diff options
| author | friendica <info@friendica.com> | 2015-01-01 22:18:27 -0800 |
|---|---|---|
| committer | friendica <info@friendica.com> | 2015-01-01 22:18:27 -0800 |
| commit | a0052f0176bd079e6a94baec59fea2ec5a8d651e (patch) | |
| tree | c323edd823681bc2e8ca757e7eaf8354d42c7b51 /library/HTMLPurifier | |
| parent | 545e47933a0816699c68d98a7742a03260d6a54f (diff) | |
| download | volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.tar.gz volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.tar.bz2 volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.zip | |
htmlpurifier update - compatibility issue with language library autoloader
Diffstat (limited to 'library/HTMLPurifier')
255 files changed, 13195 insertions, 5901 deletions
diff --git a/library/HTMLPurifier/Arborize.php b/library/HTMLPurifier/Arborize.php new file mode 100644 index 000000000..9e6617be5 --- /dev/null +++ b/library/HTMLPurifier/Arborize.php @@ -0,0 +1,71 @@ +<?php + +/** + * Converts a stream of HTMLPurifier_Token into an HTMLPurifier_Node, + * and back again. + * + * @note This transformation is not an equivalence. We mutate the input + * token stream to make it so; see all [MUT] markers in code. + */ +class HTMLPurifier_Arborize +{ + public static function arborize($tokens, $config, $context) { + $definition = $config->getHTMLDefinition(); + $parent = new HTMLPurifier_Token_Start($definition->info_parent); + $stack = array($parent->toNode()); + foreach ($tokens as $token) { + $token->skip = null; // [MUT] + $token->carryover = null; // [MUT] + if ($token instanceof HTMLPurifier_Token_End) { + $token->start = null; // [MUT] + $r = array_pop($stack); + assert($r->name === $token->name); + assert(empty($token->attr)); + $r->endCol = $token->col; + $r->endLine = $token->line; + $r->endArmor = $token->armor; + continue; + } + $node = $token->toNode(); + $stack[count($stack)-1]->children[] = $node; + if ($token instanceof HTMLPurifier_Token_Start) { + $stack[] = $node; + } + } + assert(count($stack) == 1); + return $stack[0]; + } + + public static function flatten($node, $config, $context) { + $level = 0; + $nodes = array($level => new HTMLPurifier_Queue(array($node))); + $closingTokens = array(); + $tokens = array(); + do { + while (!$nodes[$level]->isEmpty()) { + $node = $nodes[$level]->shift(); // FIFO + list($start, $end) = $node->toTokenPair(); + if ($level > 0) { + $tokens[] = $start; + } + if ($end !== NULL) { + $closingTokens[$level][] = $end; + } + if ($node instanceof HTMLPurifier_Node_Element) { + $level++; + $nodes[$level] = new HTMLPurifier_Queue(); + foreach ($node->children as $childNode) { + $nodes[$level]->push($childNode); + } + } + } + $level--; + if ($level && isset($closingTokens[$level])) { + while ($token = array_pop($closingTokens[$level])) { + $tokens[] = $token; + } + } + } while ($level > 0); + return $tokens; + } +} diff --git a/library/HTMLPurifier/AttrCollections.php b/library/HTMLPurifier/AttrCollections.php index 555b86d04..4f6c2e39a 100644 --- a/library/HTMLPurifier/AttrCollections.php +++ b/library/HTMLPurifier/AttrCollections.php @@ -8,7 +8,8 @@ class HTMLPurifier_AttrCollections { /** - * Associative array of attribute collections, indexed by name + * Associative array of attribute collections, indexed by name. + * @type array */ public $info = array(); @@ -16,10 +17,11 @@ class HTMLPurifier_AttrCollections * Performs all expansions on internal data for use by other inclusions * It also collects all attribute collection extensions from * modules - * @param $attr_types HTMLPurifier_AttrTypes instance - * @param $modules Hash array of HTMLPurifier_HTMLModule members + * @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance + * @param HTMLPurifier_HTMLModule[] $modules Hash array of HTMLPurifier_HTMLModule members */ - public function __construct($attr_types, $modules) { + public function __construct($attr_types, $modules) + { // load extensions from the modules foreach ($modules as $module) { foreach ($module->attr_collections as $coll_i => $coll) { @@ -30,7 +32,9 @@ class HTMLPurifier_AttrCollections if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) { // merge in includes $this->info[$coll_i][$attr_i] = array_merge( - $this->info[$coll_i][$attr_i], $attr); + $this->info[$coll_i][$attr_i], + $attr + ); continue; } $this->info[$coll_i][$attr_i] = $attr; @@ -49,20 +53,29 @@ class HTMLPurifier_AttrCollections /** * Takes a reference to an attribute associative array and performs * all inclusions specified by the zero index. - * @param &$attr Reference to attribute array + * @param array &$attr Reference to attribute array */ - public function performInclusions(&$attr) { - if (!isset($attr[0])) return; + public function performInclusions(&$attr) + { + if (!isset($attr[0])) { + return; + } $merge = $attr[0]; $seen = array(); // recursion guard // loop through all the inclusions for ($i = 0; isset($merge[$i]); $i++) { - if (isset($seen[$merge[$i]])) continue; + if (isset($seen[$merge[$i]])) { + continue; + } $seen[$merge[$i]] = true; // foreach attribute of the inclusion, copy it over - if (!isset($this->info[$merge[$i]])) continue; + if (!isset($this->info[$merge[$i]])) { + continue; + } foreach ($this->info[$merge[$i]] as $key => $value) { - if (isset($attr[$key])) continue; // also catches more inclusions + if (isset($attr[$key])) { + continue; + } // also catches more inclusions $attr[$key] = $value; } if (isset($this->info[$merge[$i]][0])) { @@ -76,20 +89,24 @@ class HTMLPurifier_AttrCollections /** * Expands all string identifiers in an attribute array by replacing * them with the appropriate values inside HTMLPurifier_AttrTypes - * @param &$attr Reference to attribute array - * @param $attr_types HTMLPurifier_AttrTypes instance + * @param array &$attr Reference to attribute array + * @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance */ - public function expandIdentifiers(&$attr, $attr_types) { - + public function expandIdentifiers(&$attr, $attr_types) + { // because foreach will process new elements we add, make sure we // skip duplicates $processed = array(); foreach ($attr as $def_i => $def) { // skip inclusions - if ($def_i === 0) continue; + if ($def_i === 0) { + continue; + } - if (isset($processed[$def_i])) continue; + if (isset($processed[$def_i])) { + continue; + } // determine whether or not attribute is required if ($required = (strpos($def_i, '*') !== false)) { @@ -120,9 +137,7 @@ class HTMLPurifier_AttrCollections unset($attr[$def_i]); } } - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef.php b/library/HTMLPurifier/AttrDef.php index b2e4f36c5..5ac06522b 100644 --- a/library/HTMLPurifier/AttrDef.php +++ b/library/HTMLPurifier/AttrDef.php @@ -14,23 +14,25 @@ abstract class HTMLPurifier_AttrDef { /** - * Tells us whether or not an HTML attribute is minimized. Has no - * meaning in other contexts. + * Tells us whether or not an HTML attribute is minimized. + * Has no meaning in other contexts. + * @type bool */ public $minimized = false; /** - * Tells us whether or not an HTML attribute is required. Has no - * meaning in other contexts + * Tells us whether or not an HTML attribute is required. + * Has no meaning in other contexts + * @type bool */ public $required = false; /** * Validates and cleans passed string according to a definition. * - * @param $string String to be validated and cleaned. - * @param $config Mandatory HTMLPurifier_Config object. - * @param $context Mandatory HTMLPurifier_AttrContext object. + * @param string $string String to be validated and cleaned. + * @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object. + * @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object. */ abstract public function validate($string, $config, $context); @@ -55,7 +57,8 @@ abstract class HTMLPurifier_AttrDef * parsing XML, thus, this behavior may still be correct. We * assume that newlines have been normalized. */ - public function parseCDATA($string) { + public function parseCDATA($string) + { $string = trim($string); $string = str_replace(array("\n", "\t", "\r"), ' ', $string); return $string; @@ -63,10 +66,11 @@ abstract class HTMLPurifier_AttrDef /** * Factory method for creating this class from a string. - * @param $string String construction info - * @return Created AttrDef object corresponding to $string + * @param string $string String construction info + * @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string */ - public function make($string) { + public function make($string) + { // default implementation, return a flyweight of this object. // If $string has an effect on the returned object (i.e. you // need to overload this method), it is best @@ -77,16 +81,20 @@ abstract class HTMLPurifier_AttrDef /** * Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work * properly. THIS IS A HACK! + * @param string $string a CSS colour definition + * @return string */ - protected function mungeRgb($string) { + protected function mungeRgb($string) + { return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string); } /** - * Parses a possibly escaped CSS string and returns the "pure" + * Parses a possibly escaped CSS string and returns the "pure" * version of it. */ - protected function expandCSSEscape($string) { + protected function expandCSSEscape($string) + { // flexibly parse it $ret = ''; for ($i = 0, $c = strlen($string); $i < $c; $i++) { @@ -99,25 +107,32 @@ abstract class HTMLPurifier_AttrDef if (ctype_xdigit($string[$i])) { $code = $string[$i]; for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) { - if (!ctype_xdigit($string[$i])) break; + if (!ctype_xdigit($string[$i])) { + break; + } $code .= $string[$i]; } // We have to be extremely careful when adding // new characters, to make sure we're not breaking // the encoding. $char = HTMLPurifier_Encoder::unichr(hexdec($code)); - if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue; + if (HTMLPurifier_Encoder::cleanUTF8($char) === '') { + continue; + } $ret .= $char; - if ($i < $c && trim($string[$i]) !== '') $i--; + if ($i < $c && trim($string[$i]) !== '') { + $i--; + } + continue; + } + if ($string[$i] === "\n") { continue; } - if ($string[$i] === "\n") continue; } $ret .= $string[$i]; } return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS.php b/library/HTMLPurifier/AttrDef/CSS.php index 953e70675..02c1641fb 100644 --- a/library/HTMLPurifier/AttrDef/CSS.php +++ b/library/HTMLPurifier/AttrDef/CSS.php @@ -14,8 +14,14 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef { - public function validate($css, $config, $context) { - + /** + * @param string $css + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($css, $config, $context) + { $css = $this->parseCDATA($css); $definition = $config->getCSSDefinition(); @@ -36,34 +42,47 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef $context->register('CurrentCSSProperty', $property); foreach ($declarations as $declaration) { - if (!$declaration) continue; - if (!strpos($declaration, ':')) continue; + if (!$declaration) { + continue; + } + if (!strpos($declaration, ':')) { + continue; + } list($property, $value) = explode(':', $declaration, 2); $property = trim($property); - $value = trim($value); + $value = trim($value); $ok = false; do { if (isset($definition->info[$property])) { $ok = true; break; } - if (ctype_lower($property)) break; + if (ctype_lower($property)) { + break; + } $property = strtolower($property); if (isset($definition->info[$property])) { $ok = true; break; } - } while(0); - if (!$ok) continue; + } while (0); + if (!$ok) { + continue; + } // inefficient call, since the validator will do this again if (strtolower(trim($value)) !== 'inherit') { // inherit works for everything (but only on the base property) $result = $definition->info[$property]->validate( - $value, $config, $context ); + $value, + $config, + $context + ); } else { $result = 'inherit'; } - if ($result === false) continue; + if ($result === false) { + continue; + } $propvalues[$property] = $result; } diff --git a/library/HTMLPurifier/AttrDef/CSS/AlphaValue.php b/library/HTMLPurifier/AttrDef/CSS/AlphaValue.php index 292c040d4..af2b83dff 100644 --- a/library/HTMLPurifier/AttrDef/CSS/AlphaValue.php +++ b/library/HTMLPurifier/AttrDef/CSS/AlphaValue.php @@ -3,19 +3,32 @@ class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number { - public function __construct() { + public function __construct() + { parent::__construct(false); // opacity is non-negative, but we will clamp it } - public function validate($number, $config, $context) { + /** + * @param string $number + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function validate($number, $config, $context) + { $result = parent::validate($number, $config, $context); - if ($result === false) return $result; - $float = (float) $result; - if ($float < 0.0) $result = '0'; - if ($float > 1.0) $result = '1'; + if ($result === false) { + return $result; + } + $float = (float)$result; + if ($float < 0.0) { + $result = '0'; + } + if ($float > 1.0) { + $result = '1'; + } return $result; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Background.php b/library/HTMLPurifier/AttrDef/CSS/Background.php index 3a3d20cd6..7f1ea3b0f 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Background.php +++ b/library/HTMLPurifier/AttrDef/CSS/Background.php @@ -9,11 +9,16 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef /** * Local copy of component validators. + * @type HTMLPurifier_AttrDef[] * @note See HTMLPurifier_AttrDef_Font::$info for a similar impl. */ protected $info; - public function __construct($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function __construct($config) + { $def = $config->getCSSDefinition(); $this->info['background-color'] = $def->info['background-color']; $this->info['background-image'] = $def->info['background-image']; @@ -22,40 +27,55 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef $this->info['background-position'] = $def->info['background-position']; } - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { // regular pre-processing $string = $this->parseCDATA($string); - if ($string === '') return false; + if ($string === '') { + return false; + } // munge rgb() decl if necessary $string = $this->mungeRgb($string); // assumes URI doesn't have spaces in it - $bits = explode(' ', strtolower($string)); // bits to process + $bits = explode(' ', $string); // bits to process $caught = array(); - $caught['color'] = false; - $caught['image'] = false; - $caught['repeat'] = false; + $caught['color'] = false; + $caught['image'] = false; + $caught['repeat'] = false; $caught['attachment'] = false; $caught['position'] = false; $i = 0; // number of catches - $none = false; foreach ($bits as $bit) { - if ($bit === '') continue; + if ($bit === '') { + continue; + } foreach ($caught as $key => $status) { if ($key != 'position') { - if ($status !== false) continue; + if ($status !== false) { + continue; + } $r = $this->info['background-' . $key]->validate($bit, $config, $context); } else { $r = $bit; } - if ($r === false) continue; + if ($r === false) { + continue; + } if ($key == 'position') { - if ($caught[$key] === false) $caught[$key] = ''; + if ($caught[$key] === false) { + $caught[$key] = ''; + } $caught[$key] .= $r . ' '; } else { $caught[$key] = $r; @@ -65,7 +85,9 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef } } - if (!$i) return false; + if (!$i) { + return false; + } if ($caught['position'] !== false) { $caught['position'] = $this->info['background-position']-> validate($caught['position'], $config, $context); @@ -73,15 +95,17 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef $ret = array(); foreach ($caught as $value) { - if ($value === false) continue; + if ($value === false) { + continue; + } $ret[] = $value; } - if (empty($ret)) return false; + if (empty($ret)) { + return false; + } return implode(' ', $ret); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php b/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php index fae82eaec..4580ef5a9 100644 --- a/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php +++ b/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php @@ -44,15 +44,30 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef { + /** + * @type HTMLPurifier_AttrDef_CSS_Length + */ protected $length; + + /** + * @type HTMLPurifier_AttrDef_CSS_Percentage + */ protected $percentage; - public function __construct() { - $this->length = new HTMLPurifier_AttrDef_CSS_Length(); + public function __construct() + { + $this->length = new HTMLPurifier_AttrDef_CSS_Length(); $this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage(); } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = $this->parseCDATA($string); $bits = explode(' ', $string); @@ -74,7 +89,9 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef ); foreach ($bits as $bit) { - if ($bit === '') continue; + if ($bit === '') { + continue; + } // test for keyword $lbit = ctype_lower($bit) ? $bit : strtolower($bit); @@ -104,30 +121,37 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef $measures[] = $r; $i++; } - } - if (!$i) return false; // no valid values were caught + if (!$i) { + return false; + } // no valid values were caught $ret = array(); // first keyword - if ($keywords['h']) $ret[] = $keywords['h']; - elseif ($keywords['ch']) { + if ($keywords['h']) { + $ret[] = $keywords['h']; + } elseif ($keywords['ch']) { $ret[] = $keywords['ch']; $keywords['cv'] = false; // prevent re-use: center = center center + } elseif (count($measures)) { + $ret[] = array_shift($measures); } - elseif (count($measures)) $ret[] = array_shift($measures); - if ($keywords['v']) $ret[] = $keywords['v']; - elseif ($keywords['cv']) $ret[] = $keywords['cv']; - elseif (count($measures)) $ret[] = array_shift($measures); + if ($keywords['v']) { + $ret[] = $keywords['v']; + } elseif ($keywords['cv']) { + $ret[] = $keywords['cv']; + } elseif (count($measures)) { + $ret[] = array_shift($measures); + } - if (empty($ret)) return false; + if (empty($ret)) { + return false; + } return implode(' ', $ret); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Border.php b/library/HTMLPurifier/AttrDef/CSS/Border.php index 42a1d1b4a..16243ba1e 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Border.php +++ b/library/HTMLPurifier/AttrDef/CSS/Border.php @@ -8,17 +8,29 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef /** * Local copy of properties this property is shorthand for. + * @type HTMLPurifier_AttrDef[] */ protected $info = array(); - public function __construct($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function __construct($config) + { $def = $config->getCSSDefinition(); $this->info['border-width'] = $def->info['border-width']; $this->info['border-style'] = $def->info['border-style']; $this->info['border-top-color'] = $def->info['border-top-color']; } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = $this->parseCDATA($string); $string = $this->mungeRgb($string); $bits = explode(' ', $string); @@ -26,7 +38,9 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef $ret = ''; // return value foreach ($bits as $bit) { foreach ($this->info as $propname => $validator) { - if (isset($done[$propname])) continue; + if (isset($done[$propname])) { + continue; + } $r = $validator->validate($bit, $config, $context); if ($r !== false) { $ret .= $r . ' '; @@ -37,7 +51,6 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef } return rtrim($ret); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Color.php b/library/HTMLPurifier/AttrDef/CSS/Color.php index 07f95a671..16d2a6b98 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Color.php +++ b/library/HTMLPurifier/AttrDef/CSS/Color.php @@ -6,29 +6,47 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef { - public function validate($color, $config, $context) { - + /** + * @param string $color + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($color, $config, $context) + { static $colors = null; - if ($colors === null) $colors = $config->get('Core.ColorKeywords'); + if ($colors === null) { + $colors = $config->get('Core.ColorKeywords'); + } $color = trim($color); - if ($color === '') return false; + if ($color === '') { + return false; + } $lower = strtolower($color); - if (isset($colors[$lower])) return $colors[$lower]; + if (isset($colors[$lower])) { + return $colors[$lower]; + } if (strpos($color, 'rgb(') !== false) { // rgb literal handling $length = strlen($color); - if (strpos($color, ')') !== $length - 1) return false; + if (strpos($color, ')') !== $length - 1) { + return false; + } $triad = substr($color, 4, $length - 4 - 1); $parts = explode(',', $triad); - if (count($parts) !== 3) return false; + if (count($parts) !== 3) { + return false; + } $type = false; // to ensure that they're all the same type $new_parts = array(); foreach ($parts as $part) { $part = trim($part); - if ($part === '') return false; + if ($part === '') { + return false; + } $length = strlen($part); if ($part[$length - 1] === '%') { // handle percents @@ -37,9 +55,13 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef } elseif ($type !== 'percentage') { return false; } - $num = (float) substr($part, 0, $length - 1); - if ($num < 0) $num = 0; - if ($num > 100) $num = 100; + $num = (float)substr($part, 0, $length - 1); + if ($num < 0) { + $num = 0; + } + if ($num > 100) { + $num = 100; + } $new_parts[] = "$num%"; } else { // handle integers @@ -48,10 +70,14 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef } elseif ($type !== 'integer') { return false; } - $num = (int) $part; - if ($num < 0) $num = 0; - if ($num > 255) $num = 255; - $new_parts[] = (string) $num; + $num = (int)$part; + if ($num < 0) { + $num = 0; + } + if ($num > 255) { + $num = 255; + } + $new_parts[] = (string)$num; } } $new_triad = implode(',', $new_parts); @@ -65,14 +91,15 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef $color = '#' . $color; } $length = strlen($hex); - if ($length !== 3 && $length !== 6) return false; - if (!ctype_xdigit($hex)) return false; + if ($length !== 3 && $length !== 6) { + return false; + } + if (!ctype_xdigit($hex)) { + return false; + } } - return $color; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Composite.php b/library/HTMLPurifier/AttrDef/CSS/Composite.php index de1289cba..9c1750554 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Composite.php +++ b/library/HTMLPurifier/AttrDef/CSS/Composite.php @@ -13,26 +13,36 @@ class HTMLPurifier_AttrDef_CSS_Composite extends HTMLPurifier_AttrDef { /** - * List of HTMLPurifier_AttrDef objects that may process strings + * List of objects that may process strings. + * @type HTMLPurifier_AttrDef[] * @todo Make protected */ public $defs; /** - * @param $defs List of HTMLPurifier_AttrDef objects + * @param HTMLPurifier_AttrDef[] $defs List of HTMLPurifier_AttrDef objects */ - public function __construct($defs) { + public function __construct($defs) + { $this->defs = $defs; } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { foreach ($this->defs as $i => $def) { $result = $this->defs[$i]->validate($string, $config, $context); - if ($result !== false) return $result; + if ($result !== false) { + return $result; + } } return false; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php b/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php index 6599c5b2d..9d77cc9aa 100644 --- a/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php +++ b/library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php @@ -5,22 +5,38 @@ */ class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef { - public $def, $element; + /** + * @type HTMLPurifier_AttrDef + */ + public $def; + /** + * @type string + */ + public $element; /** - * @param $def Definition to wrap - * @param $element Element to deny + * @param HTMLPurifier_AttrDef $def Definition to wrap + * @param string $element Element to deny */ - public function __construct($def, $element) { + public function __construct($def, $element) + { $this->def = $def; $this->element = $element; } + /** * Checks if CurrentToken is set and equal to $this->element + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string */ - public function validate($string, $config, $context) { + public function validate($string, $config, $context) + { $token = $context->get('CurrentToken', true); - if ($token && $token->name == $this->element) return false; + if ($token && $token->name == $this->element) { + return false; + } return $this->def->validate($string, $config, $context); } } diff --git a/library/HTMLPurifier/AttrDef/CSS/Filter.php b/library/HTMLPurifier/AttrDef/CSS/Filter.php index 147894b86..bde4c3301 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Filter.php +++ b/library/HTMLPurifier/AttrDef/CSS/Filter.php @@ -7,23 +7,37 @@ */ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef { - + /** + * @type HTMLPurifier_AttrDef_Integer + */ protected $intValidator; - public function __construct() { + public function __construct() + { $this->intValidator = new HTMLPurifier_AttrDef_Integer(); } - public function validate($value, $config, $context) { + /** + * @param string $value + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($value, $config, $context) + { $value = $this->parseCDATA($value); - if ($value === 'none') return $value; + if ($value === 'none') { + return $value; + } // if we looped this we could support multiple filters $function_length = strcspn($value, '('); $function = trim(substr($value, 0, $function_length)); if ($function !== 'alpha' && $function !== 'Alpha' && $function !== 'progid:DXImageTransform.Microsoft.Alpha' - ) return false; + ) { + return false; + } $cursor = $function_length + 1; $parameters_length = strcspn($value, ')', $cursor); $parameters = substr($value, $cursor, $parameters_length); @@ -32,15 +46,25 @@ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef $lookup = array(); foreach ($params as $param) { list($key, $value) = explode('=', $param); - $key = trim($key); + $key = trim($key); $value = trim($value); - if (isset($lookup[$key])) continue; - if ($key !== 'opacity') continue; + if (isset($lookup[$key])) { + continue; + } + if ($key !== 'opacity') { + continue; + } $value = $this->intValidator->validate($value, $config, $context); - if ($value === false) continue; - $int = (int) $value; - if ($int > 100) $value = '100'; - if ($int < 0) $value = '0'; + if ($value === false) { + continue; + } + $int = (int)$value; + if ($int > 100) { + $value = '100'; + } + if ($int < 0) { + $value = '0'; + } $ret_params[] = "$key=$value"; $lookup[$key] = true; } @@ -48,7 +72,6 @@ class HTMLPurifier_AttrDef_CSS_Filter extends HTMLPurifier_AttrDef $ret_function = "$function($ret_parameters)"; return $ret_function; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Font.php b/library/HTMLPurifier/AttrDef/CSS/Font.php index 699ee0b70..579b97ef1 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Font.php +++ b/library/HTMLPurifier/AttrDef/CSS/Font.php @@ -7,8 +7,8 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef { /** - * Local copy of component validators. - * + * Local copy of validators + * @type HTMLPurifier_AttrDef[] * @note If we moved specific CSS property definitions to their own * classes instead of having them be assembled at run time by * CSSDefinition, this wouldn't be necessary. We'd instantiate @@ -16,18 +16,28 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef */ protected $info = array(); - public function __construct($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function __construct($config) + { $def = $config->getCSSDefinition(); - $this->info['font-style'] = $def->info['font-style']; + $this->info['font-style'] = $def->info['font-style']; $this->info['font-variant'] = $def->info['font-variant']; - $this->info['font-weight'] = $def->info['font-weight']; - $this->info['font-size'] = $def->info['font-size']; - $this->info['line-height'] = $def->info['line-height']; - $this->info['font-family'] = $def->info['font-family']; + $this->info['font-weight'] = $def->info['font-weight']; + $this->info['font-size'] = $def->info['font-size']; + $this->info['line-height'] = $def->info['line-height']; + $this->info['font-family'] = $def->info['font-family']; } - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { static $system_fonts = array( 'caption' => true, 'icon' => true, @@ -39,7 +49,9 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef // regular pre-processing $string = $this->parseCDATA($string); - if ($string === '') return false; + if ($string === '') { + return false; + } // check if it's one of the keywords $lowercase_string = strtolower($string); @@ -54,15 +66,20 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef $final = ''; // output for ($i = 0, $size = count($bits); $i < $size; $i++) { - if ($bits[$i] === '') continue; + if ($bits[$i] === '') { + continue; + } switch ($stage) { - - // attempting to catch font-style, font-variant or font-weight - case 0: + case 0: // attempting to catch font-style, font-variant or font-weight foreach ($stage_1 as $validator_name) { - if (isset($caught[$validator_name])) continue; + if (isset($caught[$validator_name])) { + continue; + } $r = $this->info[$validator_name]->validate( - $bits[$i], $config, $context); + $bits[$i], + $config, + $context + ); if ($r !== false) { $final .= $r . ' '; $caught[$validator_name] = true; @@ -70,15 +87,17 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef } } // all three caught, continue on - if (count($caught) >= 3) $stage = 1; - if ($r !== false) break; - - // attempting to catch font-size and perhaps line-height - case 1: + if (count($caught) >= 3) { + $stage = 1; + } + if ($r !== false) { + break; + } + case 1: // attempting to catch font-size and perhaps line-height $found_slash = false; if (strpos($bits[$i], '/') !== false) { list($font_size, $line_height) = - explode('/', $bits[$i]); + explode('/', $bits[$i]); if ($line_height === '') { // ooh, there's a space after the slash! $line_height = false; @@ -89,14 +108,19 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef $line_height = false; } $r = $this->info['font-size']->validate( - $font_size, $config, $context); + $font_size, + $config, + $context + ); if ($r !== false) { $final .= $r; // attempt to catch line-height if ($line_height === false) { // we need to scroll forward for ($j = $i + 1; $j < $size; $j++) { - if ($bits[$j] === '') continue; + if ($bits[$j] === '') { + continue; + } if ($bits[$j] === '/') { if ($found_slash) { return false; @@ -116,7 +140,10 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef if ($found_slash) { $i = $j; $r = $this->info['line-height']->validate( - $line_height, $config, $context); + $line_height, + $config, + $context + ); if ($r !== false) { $final .= '/' . $r; } @@ -126,13 +153,14 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef break; } return false; - - // attempting to catch font-family - case 2: + case 2: // attempting to catch font-family $font_family = implode(' ', array_slice($bits, $i, $size - $i)); $r = $this->info['font-family']->validate( - $font_family, $config, $context); + $font_family, + $config, + $context + ); if ($r !== false) { $final .= $r . ' '; // processing completed successfully @@ -143,7 +171,6 @@ class HTMLPurifier_AttrDef_CSS_Font extends HTMLPurifier_AttrDef } return false; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/FontFamily.php b/library/HTMLPurifier/AttrDef/CSS/FontFamily.php index 42c2054c2..74e24c881 100644 --- a/library/HTMLPurifier/AttrDef/CSS/FontFamily.php +++ b/library/HTMLPurifier/AttrDef/CSS/FontFamily.php @@ -2,12 +2,58 @@ /** * Validates a font family list according to CSS spec - * @todo whitelisting allowed fonts would be nice */ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef { - public function validate($string, $config, $context) { + protected $mask = null; + + public function __construct() + { + $this->mask = '_- '; + for ($c = 'a'; $c <= 'z'; $c++) { + $this->mask .= $c; + } + for ($c = 'A'; $c <= 'Z'; $c++) { + $this->mask .= $c; + } + for ($c = '0'; $c <= '9'; $c++) { + $this->mask .= $c; + } // cast-y, but should be fine + // special bytes used by UTF-8 + for ($i = 0x80; $i <= 0xFF; $i++) { + // We don't bother excluding invalid bytes in this range, + // because the our restriction of well-formed UTF-8 will + // prevent these from ever occurring. + $this->mask .= chr($i); + } + + /* + PHP's internal strcspn implementation is + O(length of string * length of mask), making it inefficient + for large masks. However, it's still faster than + preg_match 8) + for (p = s1;;) { + spanp = s2; + do { + if (*spanp == c || p == s1_end) { + return p - s1; + } + } while (spanp++ < (s2_end - 1)); + c = *++p; + } + */ + // possible optimization: invert the mask. + } + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { static $generic_names = array( 'serif' => true, 'sans-serif' => true, @@ -15,24 +61,33 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef 'fantasy' => true, 'cursive' => true ); + $allowed_fonts = $config->get('CSS.AllowedFonts'); // assume that no font names contain commas in them $fonts = explode(',', $string); $final = ''; - foreach($fonts as $font) { + foreach ($fonts as $font) { $font = trim($font); - if ($font === '') continue; + if ($font === '') { + continue; + } // match a generic name if (isset($generic_names[$font])) { - $final .= $font . ', '; + if ($allowed_fonts === null || isset($allowed_fonts[$font])) { + $final .= $font . ', '; + } continue; } // match a quoted name if ($font[0] === '"' || $font[0] === "'") { $length = strlen($font); - if ($length <= 2) continue; + if ($length <= 2) { + continue; + } $quote = $font[0]; - if ($font[$length - 1] !== $quote) continue; + if ($font[$length - 1] !== $quote) { + continue; + } $font = substr($font, 1, $length - 2); } @@ -40,6 +95,10 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef // $font is a pure representation of the font name + if ($allowed_fonts !== null && !isset($allowed_fonts[$font])) { + continue; + } + if (ctype_alnum($font) && $font !== '') { // very simple font, allow it in unharmed $final .= $font . ', '; @@ -50,20 +109,108 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef // shouldn't show up regardless $font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font); - // These ugly transforms don't pose a security - // risk (as \\ and \" might). We could try to be clever and - // use single-quote wrapping when there is a double quote - // present, but I have choosen not to implement that. - // (warning: this code relies on the selection of quotation - // mark below) - $font = str_replace('\\', '\\5C ', $font); - $font = str_replace('"', '\\22 ', $font); - - // complicated font, requires quoting - $final .= "\"$font\", "; // note that this will later get turned into " + // Here, there are various classes of characters which need + // to be treated differently: + // - Alphanumeric characters are essentially safe. We + // handled these above. + // - Spaces require quoting, though most parsers will do + // the right thing if there aren't any characters that + // can be misinterpreted + // - Dashes rarely occur, but they fairly unproblematic + // for parsing/rendering purposes. + // The above characters cover the majority of Western font + // names. + // - Arbitrary Unicode characters not in ASCII. Because + // most parsers give little thought to Unicode, treatment + // of these codepoints is basically uniform, even for + // punctuation-like codepoints. These characters can + // show up in non-Western pages and are supported by most + // major browsers, for example: "ＭＳ 明朝" is a + // legitimate font-name + // <http://ja.wikipedia.org/wiki/MS_明朝>. See + // the CSS3 spec for more examples: + // <http://www.w3.org/TR/2011/WD-css3-fonts-20110324/localizedfamilynames.png> + // You can see live samples of these on the Internet: + // <http://www.google.co.jp/search?q=font-family+ＭＳ+明朝|ゴシック> + // However, most of these fonts have ASCII equivalents: + // for example, 'MS Mincho', and it's considered + // professional to use ASCII font names instead of + // Unicode font names. Thanks Takeshi Terada for + // providing this information. + // The following characters, to my knowledge, have not been + // used to name font names. + // - Single quote. While theoretically you might find a + // font name that has a single quote in its name (serving + // as an apostrophe, e.g. Dave's Scribble), I haven't + // been able to find any actual examples of this. + // Internet Explorer's cssText translation (which I + // believe is invoked by innerHTML) normalizes any + // quoting to single quotes, and fails to escape single + // quotes. (Note that this is not IE's behavior for all + // CSS properties, just some sort of special casing for + // font-family). So a single quote *cannot* be used + // safely in the font-family context if there will be an + // innerHTML/cssText translation. Note that Firefox 3.x + // does this too. + // - Double quote. In IE, these get normalized to + // single-quotes, no matter what the encoding. (Fun + // fact, in IE8, the 'content' CSS property gained + // support, where they special cased to preserve encoded + // double quotes, but still translate unadorned double + // quotes into single quotes.) So, because their + // fixpoint behavior is identical to single quotes, they + // cannot be allowed either. Firefox 3.x displays + // single-quote style behavior. + // - Backslashes are reduced by one (so \\ -> \) every + // iteration, so they cannot be used safely. This shows + // up in IE7, IE8 and FF3 + // - Semicolons, commas and backticks are handled properly. + // - The rest of the ASCII punctuation is handled properly. + // We haven't checked what browsers do to unadorned + // versions, but this is not important as long as the + // browser doesn't /remove/ surrounding quotes (as IE does + // for HTML). + // + // With these results in hand, we conclude that there are + // various levels of safety: + // - Paranoid: alphanumeric, spaces and dashes(?) + // - International: Paranoid + non-ASCII Unicode + // - Edgy: Everything except quotes, backslashes + // - NoJS: Standards compliance, e.g. sod IE. Note that + // with some judicious character escaping (since certain + // types of escaping doesn't work) this is theoretically + // OK as long as innerHTML/cssText is not called. + // We believe that international is a reasonable default + // (that we will implement now), and once we do more + // extensive research, we may feel comfortable with dropping + // it down to edgy. + + // Edgy: alphanumeric, spaces, dashes, underscores and Unicode. Use of + // str(c)spn assumes that the string was already well formed + // Unicode (which of course it is). + if (strspn($font, $this->mask) !== strlen($font)) { + continue; + } + + // Historical: + // In the absence of innerHTML/cssText, these ugly + // transforms don't pose a security risk (as \\ and \" + // might--these escapes are not supported by most browsers). + // We could try to be clever and use single-quote wrapping + // when there is a double quote present, but I have choosen + // not to implement that. (NOTE: you can reduce the amount + // of escapes by one depending on what quoting style you use) + // $font = str_replace('\\', '\\5C ', $font); + // $font = str_replace('"', '\\22 ', $font); + // $font = str_replace("'", '\\27 ', $font); + + // font possibly with spaces, requires quoting + $final .= "'$font', "; } $final = rtrim($final, ', '); - if ($final === '') return false; + if ($final === '') { + return false; + } return $final; } diff --git a/library/HTMLPurifier/AttrDef/CSS/Ident.php b/library/HTMLPurifier/AttrDef/CSS/Ident.php new file mode 100644 index 000000000..973002c17 --- /dev/null +++ b/library/HTMLPurifier/AttrDef/CSS/Ident.php @@ -0,0 +1,32 @@ +<?php + +/** + * Validates based on {ident} CSS grammar production + */ +class HTMLPurifier_AttrDef_CSS_Ident extends HTMLPurifier_AttrDef +{ + + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + $string = trim($string); + + // early abort: '' and '0' (strings that convert to false) are invalid + if (!$string) { + return false; + } + + $pattern = '/^(-?[A-Za-z_][A-Za-z_\-0-9]*)$/'; + if (!preg_match($pattern, $string)) { + return false; + } + return $string; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php b/library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php index 4e6b35e5a..ffc989fe8 100644 --- a/library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php +++ b/library/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php @@ -5,20 +5,34 @@ */ class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef { - public $def, $allow; + /** + * @type HTMLPurifier_AttrDef + */ + public $def; + /** + * @type bool + */ + public $allow; /** - * @param $def Definition to wrap - * @param $allow Whether or not to allow !important + * @param HTMLPurifier_AttrDef $def Definition to wrap + * @param bool $allow Whether or not to allow !important */ - public function __construct($def, $allow = false) { + public function __construct($def, $allow = false) + { $this->def = $def; $this->allow = $allow; } + /** * Intercepts and removes !important if necessary + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string */ - public function validate($string, $config, $context) { + public function validate($string, $config, $context) + { // test for ! and important tokens $string = trim($string); $is_important = false; @@ -32,7 +46,9 @@ class HTMLPurifier_AttrDef_CSS_ImportantDecorator extends HTMLPurifier_AttrDef } } $string = $this->def->validate($string, $config, $context); - if ($this->allow && $is_important) $string .= ' !important'; + if ($this->allow && $is_important) { + $string .= ' !important'; + } return $string; } } diff --git a/library/HTMLPurifier/AttrDef/CSS/Length.php b/library/HTMLPurifier/AttrDef/CSS/Length.php index a07ec5813..f12453a04 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Length.php +++ b/library/HTMLPurifier/AttrDef/CSS/Length.php @@ -6,42 +6,72 @@ class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef { - protected $min, $max; + /** + * @type HTMLPurifier_Length|string + */ + protected $min; /** - * @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable. - * @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable. + * @type HTMLPurifier_Length|string */ - public function __construct($min = null, $max = null) { + protected $max; + + /** + * @param HTMLPurifier_Length|string $min Minimum length, or null for no bound. String is also acceptable. + * @param HTMLPurifier_Length|string $max Maximum length, or null for no bound. String is also acceptable. + */ + public function __construct($min = null, $max = null) + { $this->min = $min !== null ? HTMLPurifier_Length::make($min) : null; $this->max = $max !== null ? HTMLPurifier_Length::make($max) : null; } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = $this->parseCDATA($string); // Optimizations - if ($string === '') return false; - if ($string === '0') return '0'; - if (strlen($string) === 1) return false; + if ($string === '') { + return false; + } + if ($string === '0') { + return '0'; + } + if (strlen($string) === 1) { + return false; + } $length = HTMLPurifier_Length::make($string); - if (!$length->isValid()) return false; + if (!$length->isValid()) { + return false; + } if ($this->min) { $c = $length->compareTo($this->min); - if ($c === false) return false; - if ($c < 0) return false; + if ($c === false) { + return false; + } + if ($c < 0) { + return false; + } } if ($this->max) { $c = $length->compareTo($this->max); - if ($c === false) return false; - if ($c > 0) return false; + if ($c === false) { + return false; + } + if ($c > 0) { + return false; + } } - return $length->toString(); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/ListStyle.php b/library/HTMLPurifier/AttrDef/CSS/ListStyle.php index 4406868c0..e74d42654 100644 --- a/library/HTMLPurifier/AttrDef/CSS/ListStyle.php +++ b/library/HTMLPurifier/AttrDef/CSS/ListStyle.php @@ -8,46 +8,72 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef { /** - * Local copy of component validators. + * Local copy of validators. + * @type HTMLPurifier_AttrDef[] * @note See HTMLPurifier_AttrDef_CSS_Font::$info for a similar impl. */ protected $info; - public function __construct($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function __construct($config) + { $def = $config->getCSSDefinition(); - $this->info['list-style-type'] = $def->info['list-style-type']; + $this->info['list-style-type'] = $def->info['list-style-type']; $this->info['list-style-position'] = $def->info['list-style-position']; $this->info['list-style-image'] = $def->info['list-style-image']; } - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { // regular pre-processing $string = $this->parseCDATA($string); - if ($string === '') return false; + if ($string === '') { + return false; + } // assumes URI doesn't have spaces in it $bits = explode(' ', strtolower($string)); // bits to process $caught = array(); - $caught['type'] = false; + $caught['type'] = false; $caught['position'] = false; - $caught['image'] = false; + $caught['image'] = false; $i = 0; // number of catches $none = false; foreach ($bits as $bit) { - if ($i >= 3) return; // optimization bit - if ($bit === '') continue; + if ($i >= 3) { + return; + } // optimization bit + if ($bit === '') { + continue; + } foreach ($caught as $key => $status) { - if ($status !== false) continue; + if ($status !== false) { + continue; + } $r = $this->info['list-style-' . $key]->validate($bit, $config, $context); - if ($r === false) continue; + if ($r === false) { + continue; + } if ($r === 'none') { - if ($none) continue; - else $none = true; - if ($key == 'image') continue; + if ($none) { + continue; + } else { + $none = true; + } + if ($key == 'image') { + continue; + } } $caught[$key] = $r; $i++; @@ -55,24 +81,32 @@ class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef } } - if (!$i) return false; + if (!$i) { + return false; + } $ret = array(); // construct type - if ($caught['type']) $ret[] = $caught['type']; + if ($caught['type']) { + $ret[] = $caught['type']; + } // construct image - if ($caught['image']) $ret[] = $caught['image']; + if ($caught['image']) { + $ret[] = $caught['image']; + } // construct position - if ($caught['position']) $ret[] = $caught['position']; + if ($caught['position']) { + $ret[] = $caught['position']; + } - if (empty($ret)) return false; + if (empty($ret)) { + return false; + } return implode(' ', $ret); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Multiple.php b/library/HTMLPurifier/AttrDef/CSS/Multiple.php index 4d62a40d7..9f266cdd1 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Multiple.php +++ b/library/HTMLPurifier/AttrDef/CSS/Multiple.php @@ -13,9 +13,9 @@ */ class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef { - /** * Instance of component definition to defer validation to. + * @type HTMLPurifier_AttrDef * @todo Make protected */ public $single; @@ -27,32 +27,45 @@ class HTMLPurifier_AttrDef_CSS_Multiple extends HTMLPurifier_AttrDef public $max; /** - * @param $single HTMLPurifier_AttrDef to multiply - * @param $max Max number of values allowed (usually four) + * @param HTMLPurifier_AttrDef $single HTMLPurifier_AttrDef to multiply + * @param int $max Max number of values allowed (usually four) */ - public function __construct($single, $max = 4) { + public function __construct($single, $max = 4) + { $this->single = $single; $this->max = $max; } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = $this->parseCDATA($string); - if ($string === '') return false; + if ($string === '') { + return false; + } $parts = explode(' ', $string); // parseCDATA replaced \r, \t and \n $length = count($parts); $final = ''; for ($i = 0, $num = 0; $i < $length && $num < $this->max; $i++) { - if (ctype_space($parts[$i])) continue; + if (ctype_space($parts[$i])) { + continue; + } $result = $this->single->validate($parts[$i], $config, $context); if ($result !== false) { $final .= $result . ' '; $num++; } } - if ($final === '') return false; + if ($final === '') { + return false; + } return rtrim($final); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Number.php b/library/HTMLPurifier/AttrDef/CSS/Number.php index 3f99e12ec..8edc159e7 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Number.php +++ b/library/HTMLPurifier/AttrDef/CSS/Number.php @@ -7,32 +7,44 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef { /** - * Bool indicating whether or not only positive values allowed. + * Indicates whether or not only positive values are allowed. + * @type bool */ protected $non_negative = false; /** - * @param $non_negative Bool indicating whether negatives are forbidden + * @param bool $non_negative indicates whether negatives are forbidden */ - public function __construct($non_negative = false) { + public function __construct($non_negative = false) + { $this->non_negative = $non_negative; } /** + * @param string $number + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string|bool * @warning Some contexts do not pass $config, $context. These * variables should not be used without checking HTMLPurifier_Length */ - public function validate($number, $config, $context) { - + public function validate($number, $config, $context) + { $number = $this->parseCDATA($number); - if ($number === '') return false; - if ($number === '0') return '0'; + if ($number === '') { + return false; + } + if ($number === '0') { + return '0'; + } $sign = ''; switch ($number[0]) { case '-': - if ($this->non_negative) return false; + if ($this->non_negative) { + return false; + } $sign = '-'; case '+': $number = substr($number, 1); @@ -44,14 +56,20 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef } // Period is the only non-numeric character allowed - if (strpos($number, '.') === false) return false; + if (strpos($number, '.') === false) { + return false; + } list($left, $right) = explode('.', $number, 2); - if ($left === '' && $right === '') return false; - if ($left !== '' && !ctype_digit($left)) return false; + if ($left === '' && $right === '') { + return false; + } + if ($left !== '' && !ctype_digit($left)) { + return false; + } - $left = ltrim($left, '0'); + $left = ltrim($left, '0'); $right = rtrim($right, '0'); if ($right === '') { @@ -59,11 +77,8 @@ class HTMLPurifier_AttrDef_CSS_Number extends HTMLPurifier_AttrDef } elseif (!ctype_digit($right)) { return false; } - return $sign . $left . '.' . $right; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/Percentage.php b/library/HTMLPurifier/AttrDef/CSS/Percentage.php index c34b8fc3c..f0f25c50a 100644 --- a/library/HTMLPurifier/AttrDef/CSS/Percentage.php +++ b/library/HTMLPurifier/AttrDef/CSS/Percentage.php @@ -7,34 +7,48 @@ class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef { /** - * Instance of HTMLPurifier_AttrDef_CSS_Number to defer number validation + * Instance to defer number validation to. + * @type HTMLPurifier_AttrDef_CSS_Number */ protected $number_def; /** - * @param Bool indicating whether to forbid negative values + * @param bool $non_negative Whether to forbid negative values */ - public function __construct($non_negative = false) { + public function __construct($non_negative = false) + { $this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative); } - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = $this->parseCDATA($string); - if ($string === '') return false; + if ($string === '') { + return false; + } $length = strlen($string); - if ($length === 1) return false; - if ($string[$length - 1] !== '%') return false; + if ($length === 1) { + return false; + } + if ($string[$length - 1] !== '%') { + return false; + } $number = substr($string, 0, $length - 1); $number = $this->number_def->validate($number, $config, $context); - if ($number === false) return false; + if ($number === false) { + return false; + } return "$number%"; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/TextDecoration.php b/library/HTMLPurifier/AttrDef/CSS/TextDecoration.php index 772c922d8..5fd4b7f7b 100644 --- a/library/HTMLPurifier/AttrDef/CSS/TextDecoration.php +++ b/library/HTMLPurifier/AttrDef/CSS/TextDecoration.php @@ -8,8 +8,14 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef { - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { static $allowed_values = array( 'line-through' => true, 'overline' => true, @@ -18,7 +24,9 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef $string = strtolower($this->parseCDATA($string)); - if ($string === 'none') return $string; + if ($string === 'none') { + return $string; + } $parts = explode(' ', $string); $final = ''; @@ -28,11 +36,11 @@ class HTMLPurifier_AttrDef_CSS_TextDecoration extends HTMLPurifier_AttrDef } } $final = rtrim($final); - if ($final === '') return false; + if ($final === '') { + return false; + } return $final; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/CSS/URI.php b/library/HTMLPurifier/AttrDef/CSS/URI.php index 1df17dc25..f9434230e 100644 --- a/library/HTMLPurifier/AttrDef/CSS/URI.php +++ b/library/HTMLPurifier/AttrDef/CSS/URI.php @@ -12,25 +12,39 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI { - public function __construct() { + public function __construct() + { parent::__construct(true); // always embedded } - public function validate($uri_string, $config, $context) { + /** + * @param string $uri_string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($uri_string, $config, $context) + { // parse the URI out of the string and then pass it onto // the parent object $uri_string = $this->parseCDATA($uri_string); - if (strpos($uri_string, 'url(') !== 0) return false; + if (strpos($uri_string, 'url(') !== 0) { + return false; + } $uri_string = substr($uri_string, 4); $new_length = strlen($uri_string) - 1; - if ($uri_string[$new_length] != ')') return false; + if ($uri_string[$new_length] != ')') { + return false; + } $uri = trim(substr($uri_string, 0, $new_length)); if (!empty($uri) && ($uri[0] == "'" || $uri[0] == '"')) { $quote = $uri[0]; $new_length = strlen($uri) - 1; - if ($uri[$new_length] !== $quote) return false; + if ($uri[$new_length] !== $quote) { + return false; + } $uri = substr($uri, 1, $new_length - 1); } @@ -38,15 +52,23 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI $result = parent::validate($uri, $config, $context); - if ($result === false) return false; + if ($result === false) { + return false; + } // extra sanity check; should have been done by URI $result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result); - return "url(\"$result\")"; + // suspicious characters are ()'; we're going to percent encode + // them for safety. + $result = str_replace(array('(', ')', "'"), array('%28', '%29', '%27'), $result); + // there's an extra bug where ampersands lose their escaping on + // an innerHTML cycle, so a very unlucky query parameter could + // then change the meaning of the URL. Unfortunately, there's + // not much we can do about that... + return "url(\"$result\")"; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/Clone.php b/library/HTMLPurifier/AttrDef/Clone.php new file mode 100644 index 000000000..6698a00c0 --- /dev/null +++ b/library/HTMLPurifier/AttrDef/Clone.php @@ -0,0 +1,44 @@ +<?php + +/** + * Dummy AttrDef that mimics another AttrDef, BUT it generates clones + * with make. + */ +class HTMLPurifier_AttrDef_Clone extends HTMLPurifier_AttrDef +{ + /** + * What we're cloning. + * @type HTMLPurifier_AttrDef + */ + protected $clone; + + /** + * @param HTMLPurifier_AttrDef $clone + */ + public function __construct($clone) + { + $this->clone = $clone; + } + + /** + * @param string $v + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($v, $config, $context) + { + return $this->clone->validate($v, $config, $context); + } + + /** + * @param string $string + * @return HTMLPurifier_AttrDef + */ + public function make($string) + { + return clone $this->clone; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/Enum.php b/library/HTMLPurifier/AttrDef/Enum.php index 5d603ebcc..8abda7f6e 100644 --- a/library/HTMLPurifier/AttrDef/Enum.php +++ b/library/HTMLPurifier/AttrDef/Enum.php @@ -12,9 +12,10 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef /** * Lookup table of valid values. + * @type array * @todo Make protected */ - public $valid_values = array(); + public $valid_values = array(); /** * Bool indicating whether or not enumeration is case sensitive. @@ -23,17 +24,23 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef protected $case_sensitive = false; // values according to W3C spec /** - * @param $valid_values List of valid values - * @param $case_sensitive Bool indicating whether or not case sensitive + * @param array $valid_values List of valid values + * @param bool $case_sensitive Whether or not case sensitive */ - public function __construct( - $valid_values = array(), $case_sensitive = false - ) { + public function __construct($valid_values = array(), $case_sensitive = false) + { $this->valid_values = array_flip($valid_values); $this->case_sensitive = $case_sensitive; } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = trim($string); if (!$this->case_sensitive) { // we may want to do full case-insensitive libraries @@ -45,11 +52,13 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef } /** - * @param $string In form of comma-delimited list of case-insensitive + * @param string $string In form of comma-delimited list of case-insensitive * valid values. Example: "foo,bar,baz". Prepend "s:" to make * case sensitive + * @return HTMLPurifier_AttrDef_Enum */ - public function make($string) { + public function make($string) + { if (strlen($string) > 2 && $string[0] == 's' && $string[1] == ':') { $string = substr($string, 2); $sensitive = true; @@ -59,7 +68,6 @@ class HTMLPurifier_AttrDef_Enum extends HTMLPurifier_AttrDef $values = explode(',', $string); return new HTMLPurifier_AttrDef_Enum($values, $sensitive); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/Bool.php b/library/HTMLPurifier/AttrDef/HTML/Bool.php index e06987eb8..036a240e1 100644 --- a/library/HTMLPurifier/AttrDef/HTML/Bool.php +++ b/library/HTMLPurifier/AttrDef/HTML/Bool.php @@ -6,23 +6,46 @@ class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef { + /** + * @type bool + */ protected $name; + + /** + * @type bool + */ public $minimized = true; - public function __construct($name = false) {$this->name = $name;} + /** + * @param bool $name + */ + public function __construct($name = false) + { + $this->name = $name; + } - public function validate($string, $config, $context) { - if (empty($string)) return false; + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + if (empty($string)) { + return false; + } return $this->name; } /** - * @param $string Name of attribute + * @param string $string Name of attribute + * @return HTMLPurifier_AttrDef_HTML_Bool */ - public function make($string) { + public function make($string) + { return new HTMLPurifier_AttrDef_HTML_Bool($string); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/Class.php b/library/HTMLPurifier/AttrDef/HTML/Class.php index 370068d97..d5013488f 100644 --- a/library/HTMLPurifier/AttrDef/HTML/Class.php +++ b/library/HTMLPurifier/AttrDef/HTML/Class.php @@ -5,7 +5,14 @@ */ class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens { - protected function split($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + protected function split($string, $config, $context) + { // really, this twiddle should be lazy loaded $name = $config->getDefinition('HTML')->doctype->name; if ($name == "XHTML 1.1" || $name == "XHTML 2.0") { @@ -14,13 +21,20 @@ class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens return preg_split('/\s+/', $string); } } - protected function filter($tokens, $config, $context) { + + /** + * @param array $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + protected function filter($tokens, $config, $context) + { $allowed = $config->get('Attr.AllowedClasses'); $forbidden = $config->get('Attr.ForbiddenClasses'); $ret = array(); foreach ($tokens as $token) { - if ( - ($allowed === null || isset($allowed[$token])) && + if (($allowed === null || isset($allowed[$token])) && !isset($forbidden[$token]) && // We need this O(n) check because of PHP's array // implementation that casts -0 to 0. diff --git a/library/HTMLPurifier/AttrDef/HTML/Color.php b/library/HTMLPurifier/AttrDef/HTML/Color.php index d01e20454..946ebb782 100644 --- a/library/HTMLPurifier/AttrDef/HTML/Color.php +++ b/library/HTMLPurifier/AttrDef/HTML/Color.php @@ -6,27 +6,46 @@ class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef { - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { static $colors = null; - if ($colors === null) $colors = $config->get('Core.ColorKeywords'); + if ($colors === null) { + $colors = $config->get('Core.ColorKeywords'); + } $string = trim($string); - if (empty($string)) return false; - if (isset($colors[$string])) return $colors[$string]; - if ($string[0] === '#') $hex = substr($string, 1); - else $hex = $string; + if (empty($string)) { + return false; + } + $lower = strtolower($string); + if (isset($colors[$lower])) { + return $colors[$lower]; + } + if ($string[0] === '#') { + $hex = substr($string, 1); + } else { + $hex = $string; + } $length = strlen($hex); - if ($length !== 3 && $length !== 6) return false; - if (!ctype_xdigit($hex)) return false; - if ($length === 3) $hex = $hex[0].$hex[0].$hex[1].$hex[1].$hex[2].$hex[2]; - + if ($length !== 3 && $length !== 6) { + return false; + } + if (!ctype_xdigit($hex)) { + return false; + } + if ($length === 3) { + $hex = $hex[0] . $hex[0] . $hex[1] . $hex[1] . $hex[2] . $hex[2]; + } return "#$hex"; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/FrameTarget.php b/library/HTMLPurifier/AttrDef/HTML/FrameTarget.php index ae6ea7c01..d79ba12b3 100644 --- a/library/HTMLPurifier/AttrDef/HTML/FrameTarget.php +++ b/library/HTMLPurifier/AttrDef/HTML/FrameTarget.php @@ -6,16 +6,33 @@ class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum { + /** + * @type array + */ public $valid_values = false; // uninitialized value + + /** + * @type bool + */ protected $case_sensitive = false; - public function __construct() {} + public function __construct() + { + } - public function validate($string, $config, $context) { - if ($this->valid_values === false) $this->valid_values = $config->get('Attr.AllowedFrameTargets'); + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { + if ($this->valid_values === false) { + $this->valid_values = $config->get('Attr.AllowedFrameTargets'); + } return parent::validate($string, $config, $context); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/ID.php b/library/HTMLPurifier/AttrDef/HTML/ID.php index 81d03762d..3d86efb44 100644 --- a/library/HTMLPurifier/AttrDef/HTML/ID.php +++ b/library/HTMLPurifier/AttrDef/HTML/ID.php @@ -12,42 +12,77 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef { - // ref functionality disabled, since we also have to verify - // whether or not the ID it refers to exists - - public function validate($id, $config, $context) { + // selector is NOT a valid thing to use for IDREFs, because IDREFs + // *must* target IDs that exist, whereas selector #ids do not. + + /** + * Determines whether or not we're validating an ID in a CSS + * selector context. + * @type bool + */ + protected $selector; + + /** + * @param bool $selector + */ + public function __construct($selector = false) + { + $this->selector = $selector; + } - if (!$config->get('Attr.EnableID')) return false; + /** + * @param string $id + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($id, $config, $context) + { + if (!$this->selector && !$config->get('Attr.EnableID')) { + return false; + } $id = trim($id); // trim it first - if ($id === '') return false; + if ($id === '') { + return false; + } $prefix = $config->get('Attr.IDPrefix'); if ($prefix !== '') { $prefix .= $config->get('Attr.IDPrefixLocal'); // prevent re-appending the prefix - if (strpos($id, $prefix) !== 0) $id = $prefix . $id; + if (strpos($id, $prefix) !== 0) { + $id = $prefix . $id; + } } elseif ($config->get('Attr.IDPrefixLocal') !== '') { - trigger_error('%Attr.IDPrefixLocal cannot be used unless '. - '%Attr.IDPrefix is set', E_USER_WARNING); + trigger_error( + '%Attr.IDPrefixLocal cannot be used unless ' . + '%Attr.IDPrefix is set', + E_USER_WARNING + ); } - //if (!$this->ref) { + if (!$this->selector) { $id_accumulator =& $context->get('IDAccumulator'); - if (isset($id_accumulator->ids[$id])) return false; - //} + if (isset($id_accumulator->ids[$id])) { + return false; + } + } // we purposely avoid using regex, hopefully this is faster if (ctype_alpha($id)) { $result = true; } else { - if (!ctype_alpha(@$id[0])) return false; - $trim = trim( // primitive style of regexps, I suppose + if (!ctype_alpha(@$id[0])) { + return false; + } + // primitive style of regexps, I suppose + $trim = trim( $id, 'A..Za..z0..9:-._' - ); + ); $result = ($trim === ''); } @@ -56,15 +91,15 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef return false; } - if (/*!$this->ref && */$result) $id_accumulator->add($id); + if (!$this->selector && $result) { + $id_accumulator->add($id); + } // if no change was made to the ID, return the result // else, return the new id if stripping whitespace made it // valid, or return false. return $result ? $id : false; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/Length.php b/library/HTMLPurifier/AttrDef/HTML/Length.php index a242f9c23..1c4006fbb 100644 --- a/library/HTMLPurifier/AttrDef/HTML/Length.php +++ b/library/HTMLPurifier/AttrDef/HTML/Length.php @@ -10,32 +10,47 @@ class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels { - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = trim($string); - if ($string === '') return false; + if ($string === '') { + return false; + } $parent_result = parent::validate($string, $config, $context); - if ($parent_result !== false) return $parent_result; + if ($parent_result !== false) { + return $parent_result; + } $length = strlen($string); $last_char = $string[$length - 1]; - if ($last_char !== '%') return false; + if ($last_char !== '%') { + return false; + } $points = substr($string, 0, $length - 1); - if (!is_numeric($points)) return false; - - $points = (int) $points; + if (!is_numeric($points)) { + return false; + } - if ($points < 0) return '0%'; - if ($points > 100) return '100%'; - - return ((string) $points) . '%'; + $points = (int)$points; + if ($points < 0) { + return '0%'; + } + if ($points > 100) { + return '100%'; + } + return ((string)$points) . '%'; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/LinkTypes.php b/library/HTMLPurifier/AttrDef/HTML/LinkTypes.php index 76d25ed08..63fa04c15 100644 --- a/library/HTMLPurifier/AttrDef/HTML/LinkTypes.php +++ b/library/HTMLPurifier/AttrDef/HTML/LinkTypes.php @@ -9,26 +9,44 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef { - /** Name config attribute to pull. */ + /** + * Name config attribute to pull. + * @type string + */ protected $name; - public function __construct($name) { + /** + * @param string $name + */ + public function __construct($name) + { $configLookup = array( 'rel' => 'AllowedRel', 'rev' => 'AllowedRev' ); if (!isset($configLookup[$name])) { - trigger_error('Unrecognized attribute name for link '. - 'relationship.', E_USER_ERROR); + trigger_error( + 'Unrecognized attribute name for link ' . + 'relationship.', + E_USER_ERROR + ); return; } $this->name = $configLookup[$name]; } - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $allowed = $config->get('Attr.' . $this->name); - if (empty($allowed)) return false; + if (empty($allowed)) { + return false; + } $string = $this->parseCDATA($string); $parts = explode(' ', $string); @@ -37,17 +55,18 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef $ret_lookup = array(); foreach ($parts as $part) { $part = strtolower(trim($part)); - if (!isset($allowed[$part])) continue; + if (!isset($allowed[$part])) { + continue; + } $ret_lookup[$part] = true; } - if (empty($ret_lookup)) return false; + if (empty($ret_lookup)) { + return false; + } $string = implode(' ', array_keys($ret_lookup)); - return $string; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/MultiLength.php b/library/HTMLPurifier/AttrDef/HTML/MultiLength.php index c72fc76e4..bbb20f2f8 100644 --- a/library/HTMLPurifier/AttrDef/HTML/MultiLength.php +++ b/library/HTMLPurifier/AttrDef/HTML/MultiLength.php @@ -9,33 +9,52 @@ class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length { - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = trim($string); - if ($string === '') return false; + if ($string === '') { + return false; + } $parent_result = parent::validate($string, $config, $context); - if ($parent_result !== false) return $parent_result; + if ($parent_result !== false) { + return $parent_result; + } $length = strlen($string); $last_char = $string[$length - 1]; - if ($last_char !== '*') return false; + if ($last_char !== '*') { + return false; + } $int = substr($string, 0, $length - 1); - if ($int == '') return '*'; - if (!is_numeric($int)) return false; - - $int = (int) $int; - - if ($int < 0) return false; - if ($int == 0) return '0'; - if ($int == 1) return '*'; - return ((string) $int) . '*'; - + if ($int == '') { + return '*'; + } + if (!is_numeric($int)) { + return false; + } + + $int = (int)$int; + if ($int < 0) { + return false; + } + if ($int == 0) { + return '0'; + } + if ($int == 1) { + return '*'; + } + return ((string)$int) . '*'; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/Nmtokens.php b/library/HTMLPurifier/AttrDef/HTML/Nmtokens.php index aa34120bd..f79683b4f 100644 --- a/library/HTMLPurifier/AttrDef/HTML/Nmtokens.php +++ b/library/HTMLPurifier/AttrDef/HTML/Nmtokens.php @@ -6,24 +6,38 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef { - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = trim($string); // early abort: '' and '0' (strings that convert to false) are invalid - if (!$string) return false; + if (!$string) { + return false; + } $tokens = $this->split($string, $config, $context); $tokens = $this->filter($tokens, $config, $context); - if (empty($tokens)) return false; + if (empty($tokens)) { + return false; + } return implode(' ', $tokens); - } /** * Splits a space separated list of tokens into its constituent parts. + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array */ - protected function split($string, $config, $context) { + protected function split($string, $config, $context) + { // OPTIMIZABLE! // do the preg_match, capture all subpatterns for reformulation @@ -31,9 +45,9 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef // escaping because I don't know how to do that with regexps // and plus it would complicate optimization efforts (you never // see that anyway). - $pattern = '/(?:(?<=\s)|\A)'. // look behind for space or string start - '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)'. - '(?:(?=\s)|\z)/'; // look ahead for space or string end + $pattern = '/(?:(?<=\s)|\A)' . // look behind for space or string start + '((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)' . + '(?:(?=\s)|\z)/'; // look ahead for space or string end preg_match_all($pattern, $string, $matches); return $matches[1]; } @@ -42,11 +56,15 @@ class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef * Template method for removing certain tokens based on arbitrary criteria. * @note If we wanted to be really functional, we'd do an array_filter * with a callback. But... we're not. + * @param array $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array */ - protected function filter($tokens, $config, $context) { + protected function filter($tokens, $config, $context) + { return $tokens; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/HTML/Pixels.php b/library/HTMLPurifier/AttrDef/HTML/Pixels.php index 4cb2c1b85..a1d019e09 100644 --- a/library/HTMLPurifier/AttrDef/HTML/Pixels.php +++ b/library/HTMLPurifier/AttrDef/HTML/Pixels.php @@ -6,43 +6,71 @@ class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef { + /** + * @type int + */ protected $max; - public function __construct($max = null) { + /** + * @param int $max + */ + public function __construct($max = null) + { $this->max = $max; } - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = trim($string); - if ($string === '0') return $string; - if ($string === '') return false; + if ($string === '0') { + return $string; + } + if ($string === '') { + return false; + } $length = strlen($string); if (substr($string, $length - 2) == 'px') { $string = substr($string, 0, $length - 2); } - if (!is_numeric($string)) return false; - $int = (int) $string; + if (!is_numeric($string)) { + return false; + } + $int = (int)$string; - if ($int < 0) return '0'; + if ($int < 0) { + return '0'; + } // upper-bound value, extremely high values can // crash operating systems, see <http://ha.ckers.org/imagecrash.html> // WARNING, above link WILL crash you if you're using Windows - if ($this->max !== null && $int > $this->max) return (string) $this->max; - - return (string) $int; - + if ($this->max !== null && $int > $this->max) { + return (string)$this->max; + } + return (string)$int; } - public function make($string) { - if ($string === '') $max = null; - else $max = (int) $string; + /** + * @param string $string + * @return HTMLPurifier_AttrDef + */ + public function make($string) + { + if ($string === '') { + $max = null; + } else { + $max = (int)$string; + } $class = get_class($this); return new $class($max); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/Integer.php b/library/HTMLPurifier/AttrDef/Integer.php index d59738d2a..400e707d2 100644 --- a/library/HTMLPurifier/AttrDef/Integer.php +++ b/library/HTMLPurifier/AttrDef/Integer.php @@ -11,17 +11,20 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef { /** - * Bool indicating whether or not negative values are allowed + * Whether or not negative values are allowed. + * @type bool */ protected $negative = true; /** - * Bool indicating whether or not zero is allowed + * Whether or not zero is allowed. + * @type bool */ protected $zero = true; /** - * Bool indicating whether or not positive values are allowed + * Whether or not positive values are allowed. + * @type bool */ protected $positive = true; @@ -30,44 +33,59 @@ class HTMLPurifier_AttrDef_Integer extends HTMLPurifier_AttrDef * @param $zero Bool indicating whether or not zero is allowed * @param $positive Bool indicating whether or not positive values are allowed */ - public function __construct( - $negative = true, $zero = true, $positive = true - ) { + public function __construct($negative = true, $zero = true, $positive = true) + { $this->negative = $negative; - $this->zero = $zero; + $this->zero = $zero; $this->positive = $positive; } - public function validate($integer, $config, $context) { - + /** + * @param string $integer + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($integer, $config, $context) + { $integer = $this->parseCDATA($integer); - if ($integer === '') return false; + if ($integer === '') { + return false; + } // we could possibly simply typecast it to integer, but there are // certain fringe cases that must not return an integer. // clip leading sign - if ( $this->negative && $integer[0] === '-' ) { + if ($this->negative && $integer[0] === '-') { $digits = substr($integer, 1); - if ($digits === '0') $integer = '0'; // rm minus sign for zero - } elseif( $this->positive && $integer[0] === '+' ) { + if ($digits === '0') { + $integer = '0'; + } // rm minus sign for zero + } elseif ($this->positive && $integer[0] === '+') { $digits = $integer = substr($integer, 1); // rm unnecessary plus } else { $digits = $integer; } // test if it's numeric - if (!ctype_digit($digits)) return false; + if (!ctype_digit($digits)) { + return false; + } // perform scope tests - if (!$this->zero && $integer == 0) return false; - if (!$this->positive && $integer > 0) return false; - if (!$this->negative && $integer < 0) return false; + if (!$this->zero && $integer == 0) { + return false; + } + if (!$this->positive && $integer > 0) { + return false; + } + if (!$this->negative && $integer < 0) { + return false; + } return $integer; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/Lang.php b/library/HTMLPurifier/AttrDef/Lang.php index 10e6da56d..2a55cea64 100644 --- a/library/HTMLPurifier/AttrDef/Lang.php +++ b/library/HTMLPurifier/AttrDef/Lang.php @@ -7,15 +7,25 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef { - public function validate($string, $config, $context) { - + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $string = trim($string); - if (!$string) return false; + if (!$string) { + return false; + } $subtags = explode('-', $string); $num_subtags = count($subtags); - if ($num_subtags == 0) return false; // sanity check + if ($num_subtags == 0) { // sanity check + return false; + } // process primary subtag : $subtags[0] $length = strlen($subtags[0]); @@ -23,15 +33,15 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef case 0: return false; case 1: - if (! ($subtags[0] == 'x' || $subtags[0] == 'i') ) { + if (!($subtags[0] == 'x' || $subtags[0] == 'i')) { return false; } break; case 2: case 3: - if (! ctype_alpha($subtags[0]) ) { + if (!ctype_alpha($subtags[0])) { return false; - } elseif (! ctype_lower($subtags[0]) ) { + } elseif (!ctype_lower($subtags[0])) { $subtags[0] = strtolower($subtags[0]); } break; @@ -40,17 +50,23 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef } $new_string = $subtags[0]; - if ($num_subtags == 1) return $new_string; + if ($num_subtags == 1) { + return $new_string; + } // process second subtag : $subtags[1] $length = strlen($subtags[1]); if ($length == 0 || ($length == 1 && $subtags[1] != 'x') || $length > 8 || !ctype_alnum($subtags[1])) { return $new_string; } - if (!ctype_lower($subtags[1])) $subtags[1] = strtolower($subtags[1]); + if (!ctype_lower($subtags[1])) { + $subtags[1] = strtolower($subtags[1]); + } $new_string .= '-' . $subtags[1]; - if ($num_subtags == 2) return $new_string; + if ($num_subtags == 2) { + return $new_string; + } // process all other subtags, index 2 and up for ($i = 2; $i < $num_subtags; $i++) { @@ -63,11 +79,8 @@ class HTMLPurifier_AttrDef_Lang extends HTMLPurifier_AttrDef } $new_string .= '-' . $subtags[$i]; } - return $new_string; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/Switch.php b/library/HTMLPurifier/AttrDef/Switch.php index c9e3ed193..c7eb3199a 100644 --- a/library/HTMLPurifier/AttrDef/Switch.php +++ b/library/HTMLPurifier/AttrDef/Switch.php @@ -6,21 +6,41 @@ class HTMLPurifier_AttrDef_Switch { + /** + * @type string + */ protected $tag; - protected $withTag, $withoutTag; + + /** + * @type HTMLPurifier_AttrDef + */ + protected $withTag; + + /** + * @type HTMLPurifier_AttrDef + */ + protected $withoutTag; /** * @param string $tag Tag name to switch upon * @param HTMLPurifier_AttrDef $with_tag Call if token matches tag * @param HTMLPurifier_AttrDef $without_tag Call if token doesn't match, or there is no token */ - public function __construct($tag, $with_tag, $without_tag) { + public function __construct($tag, $with_tag, $without_tag) + { $this->tag = $tag; $this->withTag = $with_tag; $this->withoutTag = $without_tag; } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $token = $context->get('CurrentToken', true); if (!$token || $token->name !== $this->tag) { return $this->withoutTag->validate($string, $config, $context); @@ -28,7 +48,6 @@ class HTMLPurifier_AttrDef_Switch return $this->withTag->validate($string, $config, $context); } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/Text.php b/library/HTMLPurifier/AttrDef/Text.php index c6216cc53..4553a4ea9 100644 --- a/library/HTMLPurifier/AttrDef/Text.php +++ b/library/HTMLPurifier/AttrDef/Text.php @@ -6,10 +6,16 @@ class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef { - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { return $this->parseCDATA($string); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/URI.php b/library/HTMLPurifier/AttrDef/URI.php index 01a6d83e9..c1cd89772 100644 --- a/library/HTMLPurifier/AttrDef/URI.php +++ b/library/HTMLPurifier/AttrDef/URI.php @@ -7,31 +7,54 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef { + /** + * @type HTMLPurifier_URIParser + */ protected $parser; + + /** + * @type bool + */ protected $embedsResource; /** - * @param $embeds_resource_resource Does the URI here result in an extra HTTP request? + * @param bool $embeds_resource Does the URI here result in an extra HTTP request? */ - public function __construct($embeds_resource = false) { + public function __construct($embeds_resource = false) + { $this->parser = new HTMLPurifier_URIParser(); - $this->embedsResource = (bool) $embeds_resource; + $this->embedsResource = (bool)$embeds_resource; } - public function make($string) { - $embeds = (bool) $string; + /** + * @param string $string + * @return HTMLPurifier_AttrDef_URI + */ + public function make($string) + { + $embeds = ($string === 'embedded'); return new HTMLPurifier_AttrDef_URI($embeds); } - public function validate($uri, $config, $context) { - - if ($config->get('URI.Disable')) return false; + /** + * @param string $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($uri, $config, $context) + { + if ($config->get('URI.Disable')) { + return false; + } $uri = $this->parseCDATA($uri); // parse the URI $uri = $this->parser->parse($uri); - if ($uri === false) return false; + if ($uri === false) { + return false; + } // add embedded flag to context for validators $context->register('EmbeddedURI', $this->embedsResource); @@ -41,23 +64,35 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef // generic validation $result = $uri->validate($config, $context); - if (!$result) break; + if (!$result) { + break; + } // chained filtering $uri_def = $config->getDefinition('URI'); $result = $uri_def->filter($uri, $config, $context); - if (!$result) break; + if (!$result) { + break; + } // scheme-specific validation $scheme_obj = $uri->getSchemeObj($config, $context); - if (!$scheme_obj) break; - if ($this->embedsResource && !$scheme_obj->browsable) break; + if (!$scheme_obj) { + break; + } + if ($this->embedsResource && !$scheme_obj->browsable) { + break; + } $result = $scheme_obj->validate($uri, $config, $context); - if (!$result) break; + if (!$result) { + break; + } // Post chained filtering $result = $uri_def->postFilter($uri, $config, $context); - if (!$result) break; + if (!$result) { + break; + } // survived gauntlet $ok = true; @@ -65,13 +100,12 @@ class HTMLPurifier_AttrDef_URI extends HTMLPurifier_AttrDef } while (false); $context->destroy('EmbeddedURI'); - if (!$ok) return false; - + if (!$ok) { + return false; + } // back to string return $uri->toString(); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/URI/Email.php b/library/HTMLPurifier/AttrDef/URI/Email.php index bfee9d166..daf32b764 100644 --- a/library/HTMLPurifier/AttrDef/URI/Email.php +++ b/library/HTMLPurifier/AttrDef/URI/Email.php @@ -5,8 +5,11 @@ abstract class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef /** * Unpacks a mailbox into its display-name and address + * @param string $string + * @return mixed */ - function unpack($string) { + public function unpack($string) + { // needs to be implemented } diff --git a/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php b/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php index 94c715ab4..52c0d5968 100644 --- a/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php +++ b/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php @@ -7,15 +7,23 @@ class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email { - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { // no support for named mailboxes i.e. "Bob <bob@example.com>" // that needs more percent encoding to be done - if ($string == '') return false; + if ($string == '') { + return false; + } $string = trim($string); $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string); return $result ? $string : false; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/URI/Host.php b/library/HTMLPurifier/AttrDef/URI/Host.php index 2156c10c6..e7df800b1 100644 --- a/library/HTMLPurifier/AttrDef/URI/Host.php +++ b/library/HTMLPurifier/AttrDef/URI/Host.php @@ -7,56 +7,122 @@ class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef { /** - * Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator + * IPv4 sub-validator. + * @type HTMLPurifier_AttrDef_URI_IPv4 */ protected $ipv4; /** - * Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator + * IPv6 sub-validator. + * @type HTMLPurifier_AttrDef_URI_IPv6 */ protected $ipv6; - public function __construct() { + public function __construct() + { $this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4(); $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6(); } - public function validate($string, $config, $context) { + /** + * @param string $string + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($string, $config, $context) + { $length = strlen($string); - if ($string === '') return ''; - if ($length > 1 && $string[0] === '[' && $string[$length-1] === ']') { + // empty hostname is OK; it's usually semantically equivalent: + // the default host as defined by a URI scheme is used: + // + // If the URI scheme defines a default for host, then that + // default applies when the host subcomponent is undefined + // or when the registered name is empty (zero length). + if ($string === '') { + return ''; + } + if ($length > 1 && $string[0] === '[' && $string[$length - 1] === ']') { //IPv6 $ip = substr($string, 1, $length - 2); $valid = $this->ipv6->validate($ip, $config, $context); - if ($valid === false) return false; - return '['. $valid . ']'; + if ($valid === false) { + return false; + } + return '[' . $valid . ']'; } // need to do checks on unusual encodings too $ipv4 = $this->ipv4->validate($string, $config, $context); - if ($ipv4 !== false) return $ipv4; + if ($ipv4 !== false) { + return $ipv4; + } // A regular domain name. - // This breaks I18N domain names, but we don't have proper IRI support, - // so force users to insert Punycode. If there's complaining we'll - // try to fix things into an international friendly form. + // This doesn't match I18N domain names, but we don't have proper IRI support, + // so force users to insert Punycode. + + // There is not a good sense in which underscores should be + // allowed, since it's technically not! (And if you go as + // far to allow everything as specified by the DNS spec... + // well, that's literally everything, modulo some space limits + // for the components and the overall name (which, by the way, + // we are NOT checking!). So we (arbitrarily) decide this: + // let's allow underscores wherever we would have allowed + // hyphens, if they are enabled. This is a pretty good match + // for browser behavior, for example, a large number of browsers + // cannot handle foo_.example.com, but foo_bar.example.com is + // fairly well supported. + $underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : ''; // The productions describing this are: $a = '[a-z]'; // alpha $an = '[a-z0-9]'; // alphanum - $and = '[a-z0-9-]'; // alphanum | "-" + $and = "[a-z0-9-$underscore]"; // alphanum | "-" // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum - $domainlabel = "$an($and*$an)?"; + $domainlabel = "$an($and*$an)?"; // toplabel = alpha | alpha *( alphanum | "-" ) alphanum - $toplabel = "$a($and*$an)?"; + $toplabel = "$a($and*$an)?"; // hostname = *( domainlabel "." ) toplabel [ "." ] - $match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string); - if (!$match) return false; + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } - return $string; - } + // If we have Net_IDNA2 support, we can support IRIs by + // punycoding them. (This is the most portable thing to do, + // since otherwise we have to assume browsers support + if ($config->get('Core.EnableIDNA')) { + $idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true)); + // we need to encode each period separately + $parts = explode('.', $string); + try { + $new_parts = array(); + foreach ($parts as $part) { + $encodable = false; + for ($i = 0, $c = strlen($part); $i < $c; $i++) { + if (ord($part[$i]) > 0x7a) { + $encodable = true; + break; + } + } + if (!$encodable) { + $new_parts[] = $part; + } else { + $new_parts[] = $idna->encode($part); + } + } + $string = implode('.', $new_parts); + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + } catch (Exception $e) { + // XXX error reporting + } + } + return false; + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/URI/IPv4.php b/library/HTMLPurifier/AttrDef/URI/IPv4.php index ec4cf591b..30ac16c9e 100644 --- a/library/HTMLPurifier/AttrDef/URI/IPv4.php +++ b/library/HTMLPurifier/AttrDef/URI/IPv4.php @@ -8,32 +8,38 @@ class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef { /** - * IPv4 regex, protected so that IPv6 can reuse it + * IPv4 regex, protected so that IPv6 can reuse it. + * @type string */ protected $ip4; - public function validate($aIP, $config, $context) { - - if (!$this->ip4) $this->_loadRegex(); - - if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) - { - return $aIP; + /** + * @param string $aIP + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($aIP, $config, $context) + { + if (!$this->ip4) { + $this->_loadRegex(); } + if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) { + return $aIP; + } return false; - } /** * Lazy load function to prevent regex from being stuffed in * cache. */ - protected function _loadRegex() { + protected function _loadRegex() + { $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255 $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})"; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrDef/URI/IPv6.php b/library/HTMLPurifier/AttrDef/URI/IPv6.php index 9454e9be5..f243793ee 100644 --- a/library/HTMLPurifier/AttrDef/URI/IPv6.php +++ b/library/HTMLPurifier/AttrDef/URI/IPv6.php @@ -9,91 +9,81 @@ class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4 { - public function validate($aIP, $config, $context) { - - if (!$this->ip4) $this->_loadRegex(); + /** + * @param string $aIP + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string + */ + public function validate($aIP, $config, $context) + { + if (!$this->ip4) { + $this->_loadRegex(); + } $original = $aIP; $hex = '[0-9a-fA-F]'; $blk = '(?:' . $hex . '{1,4})'; - $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 + $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 // prefix check - if (strpos($aIP, '/') !== false) - { - if (preg_match('#' . $pre . '$#s', $aIP, $find)) - { - $aIP = substr($aIP, 0, 0-strlen($find[0])); - unset($find); - } - else - { - return false; - } + if (strpos($aIP, '/') !== false) { + if (preg_match('#' . $pre . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + unset($find); + } else { + return false; + } } // IPv4-compatiblity check - if (preg_match('#(?<=:'.')' . $this->ip4 . '$#s', $aIP, $find)) - { - $aIP = substr($aIP, 0, 0-strlen($find[0])); - $ip = explode('.', $find[0]); - $ip = array_map('dechex', $ip); - $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; - unset($find, $ip); + if (preg_match('#(?<=:' . ')' . $this->ip4 . '$#s', $aIP, $find)) { + $aIP = substr($aIP, 0, 0 - strlen($find[0])); + $ip = explode('.', $find[0]); + $ip = array_map('dechex', $ip); + $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; + unset($find, $ip); } // compression check $aIP = explode('::', $aIP); $c = count($aIP); - if ($c > 2) - { + if ($c > 2) { + return false; + } elseif ($c == 2) { + list($first, $second) = $aIP; + $first = explode(':', $first); + $second = explode(':', $second); + + if (count($first) + count($second) > 8) { return false; - } - elseif ($c == 2) - { - list($first, $second) = $aIP; - $first = explode(':', $first); - $second = explode(':', $second); - - if (count($first) + count($second) > 8) - { - return false; - } + } - while(count($first) < 8) - { - array_push($first, '0'); - } + while (count($first) < 8) { + array_push($first, '0'); + } - array_splice($first, 8 - count($second), 8, $second); - $aIP = $first; - unset($first,$second); - } - else - { - $aIP = explode(':', $aIP[0]); + array_splice($first, 8 - count($second), 8, $second); + $aIP = $first; + unset($first, $second); + } else { + $aIP = explode(':', $aIP[0]); } $c = count($aIP); - if ($c != 8) - { - return false; + if ($c != 8) { + return false; } // All the pieces should be 16-bit hex strings. Are they? - foreach ($aIP as $piece) - { - if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) - { - return false; - } + foreach ($aIP as $piece) { + if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) { + return false; + } } - return $original; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform.php b/library/HTMLPurifier/AttrTransform.php index e61d3e01b..b428331f1 100644 --- a/library/HTMLPurifier/AttrTransform.php +++ b/library/HTMLPurifier/AttrTransform.php @@ -20,37 +20,41 @@ abstract class HTMLPurifier_AttrTransform /** * Abstract: makes changes to the attributes dependent on multiple values. * - * @param $attr Assoc array of attributes, usually from + * @param array $attr Assoc array of attributes, usually from * HTMLPurifier_Token_Tag::$attr - * @param $config Mandatory HTMLPurifier_Config object. - * @param $context Mandatory HTMLPurifier_Context object - * @returns Processed attribute array. + * @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object. + * @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object + * @return array Processed attribute array. */ abstract public function transform($attr, $config, $context); /** * Prepends CSS properties to the style attribute, creating the * attribute if it doesn't exist. - * @param $attr Attribute array to process (passed by reference) - * @param $css CSS to prepend + * @param array &$attr Attribute array to process (passed by reference) + * @param string $css CSS to prepend */ - public function prependCSS(&$attr, $css) { + public function prependCSS(&$attr, $css) + { $attr['style'] = isset($attr['style']) ? $attr['style'] : ''; $attr['style'] = $css . $attr['style']; } /** * Retrieves and removes an attribute - * @param $attr Attribute array to process (passed by reference) - * @param $key Key of attribute to confiscate + * @param array &$attr Attribute array to process (passed by reference) + * @param mixed $key Key of attribute to confiscate + * @return mixed */ - public function confiscateAttr(&$attr, $key) { - if (!isset($attr[$key])) return null; + public function confiscateAttr(&$attr, $key) + { + if (!isset($attr[$key])) { + return null; + } $value = $attr[$key]; unset($attr[$key]); return $value; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Background.php b/library/HTMLPurifier/AttrTransform/Background.php index 0e1ff24a3..2f72869a5 100644 --- a/library/HTMLPurifier/AttrTransform/Background.php +++ b/library/HTMLPurifier/AttrTransform/Background.php @@ -3,21 +3,26 @@ /** * Pre-transform that changes proprietary background attribute to CSS. */ -class HTMLPurifier_AttrTransform_Background extends HTMLPurifier_AttrTransform { - - public function transform($attr, $config, $context) { - - if (!isset($attr['background'])) return $attr; +class HTMLPurifier_AttrTransform_Background extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['background'])) { + return $attr; + } $background = $this->confiscateAttr($attr, 'background'); // some validation should happen here $this->prependCSS($attr, "background-image:url($background);"); - return $attr; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/BdoDir.php b/library/HTMLPurifier/AttrTransform/BdoDir.php index 4d1a05665..d66c04a5b 100644 --- a/library/HTMLPurifier/AttrTransform/BdoDir.php +++ b/library/HTMLPurifier/AttrTransform/BdoDir.php @@ -8,12 +8,20 @@ class HTMLPurifier_AttrTransform_BdoDir extends HTMLPurifier_AttrTransform { - public function transform($attr, $config, $context) { - if (isset($attr['dir'])) return $attr; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (isset($attr['dir'])) { + return $attr; + } $attr['dir'] = $config->get('Attr.DefaultTextDir'); return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/BgColor.php b/library/HTMLPurifier/AttrTransform/BgColor.php index ad3916bb9..0f51fd2ce 100644 --- a/library/HTMLPurifier/AttrTransform/BgColor.php +++ b/library/HTMLPurifier/AttrTransform/BgColor.php @@ -3,21 +3,26 @@ /** * Pre-transform that changes deprecated bgcolor attribute to CSS. */ -class HTMLPurifier_AttrTransform_BgColor extends HTMLPurifier_AttrTransform { - - public function transform($attr, $config, $context) { - - if (!isset($attr['bgcolor'])) return $attr; +class HTMLPurifier_AttrTransform_BgColor extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['bgcolor'])) { + return $attr; + } $bgcolor = $this->confiscateAttr($attr, 'bgcolor'); // some validation should happen here $this->prependCSS($attr, "background-color:$bgcolor;"); - return $attr; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/BoolToCSS.php b/library/HTMLPurifier/AttrTransform/BoolToCSS.php index 51159b671..f25cd0195 100644 --- a/library/HTMLPurifier/AttrTransform/BoolToCSS.php +++ b/library/HTMLPurifier/AttrTransform/BoolToCSS.php @@ -3,34 +3,45 @@ /** * Pre-transform that changes converts a boolean attribute to fixed CSS */ -class HTMLPurifier_AttrTransform_BoolToCSS extends HTMLPurifier_AttrTransform { - +class HTMLPurifier_AttrTransform_BoolToCSS extends HTMLPurifier_AttrTransform +{ /** - * Name of boolean attribute that is trigger + * Name of boolean attribute that is trigger. + * @type string */ protected $attr; /** - * CSS declarations to add to style, needs trailing semicolon + * CSS declarations to add to style, needs trailing semicolon. + * @type string */ protected $css; /** - * @param $attr string attribute name to convert from - * @param $css string CSS declarations to add to style (needs semicolon) + * @param string $attr attribute name to convert from + * @param string $css CSS declarations to add to style (needs semicolon) */ - public function __construct($attr, $css) { + public function __construct($attr, $css) + { $this->attr = $attr; - $this->css = $css; + $this->css = $css; } - public function transform($attr, $config, $context) { - if (!isset($attr[$this->attr])) return $attr; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } unset($attr[$this->attr]); $this->prependCSS($attr, $this->css); return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Border.php b/library/HTMLPurifier/AttrTransform/Border.php index 476b0b079..057dc017f 100644 --- a/library/HTMLPurifier/AttrTransform/Border.php +++ b/library/HTMLPurifier/AttrTransform/Border.php @@ -3,16 +3,24 @@ /** * Pre-transform that changes deprecated border attribute to CSS. */ -class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform { - - public function transform($attr, $config, $context) { - if (!isset($attr['border'])) return $attr; +class HTMLPurifier_AttrTransform_Border extends HTMLPurifier_AttrTransform +{ + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['border'])) { + return $attr; + } $border_width = $this->confiscateAttr($attr, 'border'); // some validation should happen here $this->prependCSS($attr, "border:{$border_width}px solid;"); return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/EnumToCSS.php b/library/HTMLPurifier/AttrTransform/EnumToCSS.php index 2a5b4514a..7ccd0e3fb 100644 --- a/library/HTMLPurifier/AttrTransform/EnumToCSS.php +++ b/library/HTMLPurifier/AttrTransform/EnumToCSS.php @@ -4,55 +4,65 @@ * Generic pre-transform that converts an attribute with a fixed number of * values (enumerated) to CSS. */ -class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform { - +class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform +{ /** - * Name of attribute to transform from + * Name of attribute to transform from. + * @type string */ protected $attr; /** - * Lookup array of attribute values to CSS + * Lookup array of attribute values to CSS. + * @type array */ protected $enumToCSS = array(); /** - * Case sensitivity of the matching + * Case sensitivity of the matching. + * @type bool * @warning Currently can only be guaranteed to work with ASCII * values. */ protected $caseSensitive = false; /** - * @param $attr String attribute name to transform from - * @param $enumToCSS Lookup array of attribute values to CSS - * @param $case_sensitive Boolean case sensitivity indicator, default false + * @param string $attr Attribute name to transform from + * @param array $enum_to_css Lookup array of attribute values to CSS + * @param bool $case_sensitive Case sensitivity indicator, default false */ - public function __construct($attr, $enum_to_css, $case_sensitive = false) { + public function __construct($attr, $enum_to_css, $case_sensitive = false) + { $this->attr = $attr; $this->enumToCSS = $enum_to_css; - $this->caseSensitive = (bool) $case_sensitive; + $this->caseSensitive = (bool)$case_sensitive; } - public function transform($attr, $config, $context) { - - if (!isset($attr[$this->attr])) return $attr; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } $value = trim($attr[$this->attr]); unset($attr[$this->attr]); - if (!$this->caseSensitive) $value = strtolower($value); + if (!$this->caseSensitive) { + $value = strtolower($value); + } if (!isset($this->enumToCSS[$value])) { return $attr; } - $this->prependCSS($attr, $this->enumToCSS[$value]); - return $attr; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/ImgRequired.php b/library/HTMLPurifier/AttrTransform/ImgRequired.php index 7f0e4b7a5..7df6cb3e1 100644 --- a/library/HTMLPurifier/AttrTransform/ImgRequired.php +++ b/library/HTMLPurifier/AttrTransform/ImgRequired.php @@ -11,11 +11,19 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform { - public function transform($attr, $config, $context) { - + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { $src = true; if (!isset($attr['src'])) { - if ($config->get('Core.RemoveInvalidImg')) return $attr; + if ($config->get('Core.RemoveInvalidImg')) { + return $attr; + } $attr['src'] = $config->get('Attr.DefaultInvalidImage'); $src = false; } @@ -25,7 +33,7 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform $alt = $config->get('Attr.DefaultImageAlt'); if ($alt === null) { // truncate if the alt is too long - $attr['alt'] = substr(basename($attr['src']),0,40); + $attr['alt'] = substr(basename($attr['src']), 0, 40); } else { $attr['alt'] = $alt; } @@ -33,11 +41,8 @@ class HTMLPurifier_AttrTransform_ImgRequired extends HTMLPurifier_AttrTransform $attr['alt'] = $config->get('Attr.DefaultInvalidImageAlt'); } } - return $attr; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/ImgSpace.php b/library/HTMLPurifier/AttrTransform/ImgSpace.php index fd84c10c3..350b3358f 100644 --- a/library/HTMLPurifier/AttrTransform/ImgSpace.php +++ b/library/HTMLPurifier/AttrTransform/ImgSpace.php @@ -3,42 +3,59 @@ /** * Pre-transform that changes deprecated hspace and vspace attributes to CSS */ -class HTMLPurifier_AttrTransform_ImgSpace extends HTMLPurifier_AttrTransform { - +class HTMLPurifier_AttrTransform_ImgSpace extends HTMLPurifier_AttrTransform +{ + /** + * @type string + */ protected $attr; + + /** + * @type array + */ protected $css = array( 'hspace' => array('left', 'right'), 'vspace' => array('top', 'bottom') ); - public function __construct($attr) { + /** + * @param string $attr + */ + public function __construct($attr) + { $this->attr = $attr; if (!isset($this->css[$attr])) { trigger_error(htmlspecialchars($attr) . ' is not valid space attribute'); } } - public function transform($attr, $config, $context) { - - if (!isset($attr[$this->attr])) return $attr; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->attr])) { + return $attr; + } $width = $this->confiscateAttr($attr, $this->attr); // some validation could happen here - if (!isset($this->css[$this->attr])) return $attr; + if (!isset($this->css[$this->attr])) { + return $attr; + } $style = ''; foreach ($this->css[$this->attr] as $suffix) { $property = "margin-$suffix"; $style .= "$property:{$width}px;"; } - $this->prependCSS($attr, $style); - return $attr; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Input.php b/library/HTMLPurifier/AttrTransform/Input.php index 16829552d..3ab47ed8c 100644 --- a/library/HTMLPurifier/AttrTransform/Input.php +++ b/library/HTMLPurifier/AttrTransform/Input.php @@ -4,17 +4,31 @@ * Performs miscellaneous cross attribute validation and filtering for * input elements. This is meant to be a post-transform. */ -class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform { - +class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform +{ + /** + * @type HTMLPurifier_AttrDef_HTML_Pixels + */ protected $pixels; - public function __construct() { + public function __construct() + { $this->pixels = new HTMLPurifier_AttrDef_HTML_Pixels(); } - public function transform($attr, $config, $context) { - if (!isset($attr['type'])) $t = 'text'; - else $t = strtolower($attr['type']); + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['type'])) { + $t = 'text'; + } else { + $t = strtolower($attr['type']); + } if (isset($attr['checked']) && $t !== 'radio' && $t !== 'checkbox') { unset($attr['checked']); } @@ -23,8 +37,11 @@ class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform { } if (isset($attr['size']) && $t !== 'text' && $t !== 'password') { $result = $this->pixels->validate($attr['size'], $config, $context); - if ($result === false) unset($attr['size']); - else $attr['size'] = $result; + if ($result === false) { + unset($attr['size']); + } else { + $attr['size'] = $result; + } } if (isset($attr['src']) && $t !== 'image') { unset($attr['src']); @@ -34,7 +51,6 @@ class HTMLPurifier_AttrTransform_Input extends HTMLPurifier_AttrTransform { } return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Lang.php b/library/HTMLPurifier/AttrTransform/Lang.php index 5869e7f82..5b0aff0e4 100644 --- a/library/HTMLPurifier/AttrTransform/Lang.php +++ b/library/HTMLPurifier/AttrTransform/Lang.php @@ -8,9 +8,15 @@ class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform { - public function transform($attr, $config, $context) { - - $lang = isset($attr['lang']) ? $attr['lang'] : false; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + $lang = isset($attr['lang']) ? $attr['lang'] : false; $xml_lang = isset($attr['xml:lang']) ? $attr['xml:lang'] : false; if ($lang !== false && $xml_lang === false) { @@ -18,11 +24,8 @@ class HTMLPurifier_AttrTransform_Lang extends HTMLPurifier_AttrTransform } elseif ($xml_lang !== false) { $attr['lang'] = $xml_lang; } - return $attr; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Length.php b/library/HTMLPurifier/AttrTransform/Length.php index ea2f30473..853f33549 100644 --- a/library/HTMLPurifier/AttrTransform/Length.php +++ b/library/HTMLPurifier/AttrTransform/Length.php @@ -6,22 +6,40 @@ class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform { + /** + * @type string + */ protected $name; + + /** + * @type string + */ protected $cssName; - public function __construct($name, $css_name = null) { + public function __construct($name, $css_name = null) + { $this->name = $name; $this->cssName = $css_name ? $css_name : $name; } - public function transform($attr, $config, $context) { - if (!isset($attr[$this->name])) return $attr; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr[$this->name])) { + return $attr; + } $length = $this->confiscateAttr($attr, $this->name); - if(ctype_digit($length)) $length .= 'px'; + if (ctype_digit($length)) { + $length .= 'px'; + } $this->prependCSS($attr, $this->cssName . ":$length;"); return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Name.php b/library/HTMLPurifier/AttrTransform/Name.php index 15315bc73..63cce6837 100644 --- a/library/HTMLPurifier/AttrTransform/Name.php +++ b/library/HTMLPurifier/AttrTransform/Name.php @@ -6,16 +6,28 @@ class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform { - public function transform($attr, $config, $context) { + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { // Abort early if we're using relaxed definition of name - if ($config->get('HTML.Attr.Name.UseCDATA')) return $attr; - if (!isset($attr['name'])) return $attr; + if ($config->get('HTML.Attr.Name.UseCDATA')) { + return $attr; + } + if (!isset($attr['name'])) { + return $attr; + } $id = $this->confiscateAttr($attr, 'name'); - if ( isset($attr['id'])) return $attr; + if (isset($attr['id'])) { + return $attr; + } $attr['id'] = $id; return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/NameSync.php b/library/HTMLPurifier/AttrTransform/NameSync.php index a95638c14..36079b786 100644 --- a/library/HTMLPurifier/AttrTransform/NameSync.php +++ b/library/HTMLPurifier/AttrTransform/NameSync.php @@ -8,20 +8,34 @@ class HTMLPurifier_AttrTransform_NameSync extends HTMLPurifier_AttrTransform { - public function __construct() { + public function __construct() + { $this->idDef = new HTMLPurifier_AttrDef_HTML_ID(); } - public function transform($attr, $config, $context) { - if (!isset($attr['name'])) return $attr; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['name'])) { + return $attr; + } $name = $attr['name']; - if (isset($attr['id']) && $attr['id'] === $name) return $attr; + if (isset($attr['id']) && $attr['id'] === $name) { + return $attr; + } $result = $this->idDef->validate($name, $config, $context); - if ($result === false) unset($attr['name']); - else $attr['name'] = $result; + if ($result === false) { + unset($attr['name']); + } else { + $attr['name'] = $result; + } return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Nofollow.php b/library/HTMLPurifier/AttrTransform/Nofollow.php new file mode 100644 index 000000000..1057ebee1 --- /dev/null +++ b/library/HTMLPurifier/AttrTransform/Nofollow.php @@ -0,0 +1,52 @@ +<?php + +// must be called POST validation + +/** + * Adds rel="nofollow" to all outbound links. This transform is + * only attached if Attr.Nofollow is TRUE. + */ +class HTMLPurifier_AttrTransform_Nofollow extends HTMLPurifier_AttrTransform +{ + /** + * @type HTMLPurifier_URIParser + */ + private $parser; + + public function __construct() + { + $this->parser = new HTMLPurifier_URIParser(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['href'])) { + return $attr; + } + + // XXX Kind of inefficient + $url = $this->parser->parse($attr['href']); + $scheme = $url->getSchemeObj($config, $context); + + if ($scheme->browsable && !$url->isLocal($config, $context)) { + if (isset($attr['rel'])) { + $rels = explode(' ', $attr['rel']); + if (!in_array('nofollow', $rels)) { + $rels[] = 'nofollow'; + } + $attr['rel'] = implode(' ', $rels); + } else { + $attr['rel'] = 'nofollow'; + } + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/SafeEmbed.php b/library/HTMLPurifier/AttrTransform/SafeEmbed.php index 4da449981..231c81a3f 100644 --- a/library/HTMLPurifier/AttrTransform/SafeEmbed.php +++ b/library/HTMLPurifier/AttrTransform/SafeEmbed.php @@ -2,9 +2,19 @@ class HTMLPurifier_AttrTransform_SafeEmbed extends HTMLPurifier_AttrTransform { + /** + * @type string + */ public $name = "SafeEmbed"; - public function transform($attr, $config, $context) { + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { $attr['allowscriptaccess'] = 'never'; $attr['allownetworking'] = 'internal'; $attr['type'] = 'application/x-shockwave-flash'; diff --git a/library/HTMLPurifier/AttrTransform/SafeObject.php b/library/HTMLPurifier/AttrTransform/SafeObject.php index 1ed74898b..d1f3a4d2e 100644 --- a/library/HTMLPurifier/AttrTransform/SafeObject.php +++ b/library/HTMLPurifier/AttrTransform/SafeObject.php @@ -5,10 +5,22 @@ */ class HTMLPurifier_AttrTransform_SafeObject extends HTMLPurifier_AttrTransform { + /** + * @type string + */ public $name = "SafeObject"; - function transform($attr, $config, $context) { - if (!isset($attr['type'])) $attr['type'] = 'application/x-shockwave-flash'; + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['type'])) { + $attr['type'] = 'application/x-shockwave-flash'; + } return $attr; } } diff --git a/library/HTMLPurifier/AttrTransform/SafeParam.php b/library/HTMLPurifier/AttrTransform/SafeParam.php index 3f992ec31..1143b4b49 100644 --- a/library/HTMLPurifier/AttrTransform/SafeParam.php +++ b/library/HTMLPurifier/AttrTransform/SafeParam.php @@ -14,14 +14,30 @@ */ class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform { + /** + * @type string + */ public $name = "SafeParam"; + + /** + * @type HTMLPurifier_AttrDef_URI + */ private $uri; - public function __construct() { + public function __construct() + { $this->uri = new HTMLPurifier_AttrDef_URI(true); // embedded + $this->wmode = new HTMLPurifier_AttrDef_Enum(array('window', 'opaque', 'transparent')); } - public function transform($attr, $config, $context) { + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { // If we add support for other objects, we'll need to alter the // transforms. switch ($attr['name']) { @@ -33,8 +49,15 @@ class HTMLPurifier_AttrTransform_SafeParam extends HTMLPurifier_AttrTransform case 'allowNetworking': $attr['value'] = 'internal'; break; + case 'allowFullScreen': + if ($config->get('HTML.FlashAllowFullScreen')) { + $attr['value'] = ($attr['value'] == 'true') ? 'true' : 'false'; + } else { + $attr['value'] = 'false'; + } + break; case 'wmode': - $attr['value'] = 'window'; + $attr['value'] = $this->wmode->validate($attr['value'], $config, $context); break; case 'movie': case 'src': diff --git a/library/HTMLPurifier/AttrTransform/ScriptRequired.php b/library/HTMLPurifier/AttrTransform/ScriptRequired.php index 4499050a2..b7057bbf8 100644 --- a/library/HTMLPurifier/AttrTransform/ScriptRequired.php +++ b/library/HTMLPurifier/AttrTransform/ScriptRequired.php @@ -5,7 +5,14 @@ */ class HTMLPurifier_AttrTransform_ScriptRequired extends HTMLPurifier_AttrTransform { - public function transform($attr, $config, $context) { + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { if (!isset($attr['type'])) { $attr['type'] = 'text/javascript'; } diff --git a/library/HTMLPurifier/AttrTransform/TargetBlank.php b/library/HTMLPurifier/AttrTransform/TargetBlank.php new file mode 100644 index 000000000..dd63ea89c --- /dev/null +++ b/library/HTMLPurifier/AttrTransform/TargetBlank.php @@ -0,0 +1,45 @@ +<?php + +// must be called POST validation + +/** + * Adds target="blank" to all outbound links. This transform is + * only attached if Attr.TargetBlank is TRUE. This works regardless + * of whether or not Attr.AllowedFrameTargets + */ +class HTMLPurifier_AttrTransform_TargetBlank extends HTMLPurifier_AttrTransform +{ + /** + * @type HTMLPurifier_URIParser + */ + private $parser; + + public function __construct() + { + $this->parser = new HTMLPurifier_URIParser(); + } + + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { + if (!isset($attr['href'])) { + return $attr; + } + + // XXX Kind of inefficient + $url = $this->parser->parse($attr['href']); + $scheme = $url->getSchemeObj($config, $context); + + if ($scheme->browsable && !$url->isBenign($config, $context)) { + $attr['target'] = '_blank'; + } + return $attr; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTransform/Textarea.php b/library/HTMLPurifier/AttrTransform/Textarea.php index 81ac3488b..6a9f33a0c 100644 --- a/library/HTMLPurifier/AttrTransform/Textarea.php +++ b/library/HTMLPurifier/AttrTransform/Textarea.php @@ -5,14 +5,23 @@ */ class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform { - - public function transform($attr, $config, $context) { + /** + * @param array $attr + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function transform($attr, $config, $context) + { // Calculated from Firefox - if (!isset($attr['cols'])) $attr['cols'] = '22'; - if (!isset($attr['rows'])) $attr['rows'] = '3'; + if (!isset($attr['cols'])) { + $attr['cols'] = '22'; + } + if (!isset($attr['rows'])) { + $attr['rows'] = '3'; + } return $attr; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/AttrTypes.php b/library/HTMLPurifier/AttrTypes.php index fc2ea4e58..3b70520b6 100644 --- a/library/HTMLPurifier/AttrTypes.php +++ b/library/HTMLPurifier/AttrTypes.php @@ -6,7 +6,8 @@ class HTMLPurifier_AttrTypes { /** - * Lookup array of attribute string identifiers to concrete implementations + * Lookup array of attribute string identifiers to concrete implementations. + * @type HTMLPurifier_AttrDef[] */ protected $info = array(); @@ -14,7 +15,15 @@ class HTMLPurifier_AttrTypes * Constructs the info array, supplying default implementations for attribute * types. */ - public function __construct() { + public function __construct() + { + // XXX This is kind of poor, since we don't actually /clone/ + // instances; instead, we use the supplied make() attribute. So, + // the underlying class must know how to deal with arguments. + // With the old implementation of Enum, that ignored its + // arguments when handling a make dispatch, the IAlign + // definition wouldn't work. + // pseudo-types, must be instantiated via shorthand $this->info['Enum'] = new HTMLPurifier_AttrDef_Enum(); $this->info['Bool'] = new HTMLPurifier_AttrDef_HTML_Bool(); @@ -29,6 +38,9 @@ class HTMLPurifier_AttrTypes $this->info['URI'] = new HTMLPurifier_AttrDef_URI(); $this->info['LanguageCode'] = new HTMLPurifier_AttrDef_Lang(); $this->info['Color'] = new HTMLPurifier_AttrDef_HTML_Color(); + $this->info['IAlign'] = self::makeEnum('top,middle,bottom,left,right'); + $this->info['LAlign'] = self::makeEnum('top,bottom,left,right'); + $this->info['FrameTarget'] = new HTMLPurifier_AttrDef_HTML_FrameTarget(); // unimplemented aliases $this->info['ContentType'] = new HTMLPurifier_AttrDef_Text(); @@ -44,32 +56,39 @@ class HTMLPurifier_AttrTypes $this->info['Number'] = new HTMLPurifier_AttrDef_Integer(false, false, true); } + private static function makeEnum($in) + { + return new HTMLPurifier_AttrDef_Clone(new HTMLPurifier_AttrDef_Enum(explode(',', $in))); + } + /** * Retrieves a type - * @param $type String type name - * @return Object AttrDef for type + * @param string $type String type name + * @return HTMLPurifier_AttrDef Object AttrDef for type */ - public function get($type) { - + public function get($type) + { // determine if there is any extra info tacked on - if (strpos($type, '#') !== false) list($type, $string) = explode('#', $type, 2); - else $string = ''; + if (strpos($type, '#') !== false) { + list($type, $string) = explode('#', $type, 2); + } else { + $string = ''; + } if (!isset($this->info[$type])) { trigger_error('Cannot retrieve undefined attribute type ' . $type, E_USER_ERROR); return; } - return $this->info[$type]->make($string); - } /** * Sets a new implementation for a type - * @param $type String type name - * @param $impl Object AttrDef for type + * @param string $type String type name + * @param HTMLPurifier_AttrDef $impl Object AttrDef for type */ - public function set($type, $impl) { + public function set($type, $impl) + { $this->info[$type] = $impl; } } diff --git a/library/HTMLPurifier/AttrValidator.php b/library/HTMLPurifier/AttrValidator.php index 829a0f8f2..f97dc93ed 100644 --- a/library/HTMLPurifier/AttrValidator.php +++ b/library/HTMLPurifier/AttrValidator.php @@ -9,17 +9,14 @@ class HTMLPurifier_AttrValidator { /** - * Validates the attributes of a token, returning a modified token + * Validates the attributes of a token, mutating it as necessary. * that has valid tokens - * @param $token Reference to token to validate. We require a reference - * because the operation this class performs on the token are - * not atomic, so the context CurrentToken to be updated - * throughout - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context + * @param HTMLPurifier_Token $token Token to validate. + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config + * @param HTMLPurifier_Context $context Instance of HTMLPurifier_Context */ - public function validateToken(&$token, &$config, $context) { - + public function validateToken($token, $config, $context) + { $definition = $config->getHTMLDefinition(); $e =& $context->get('ErrorCollector', true); @@ -32,12 +29,15 @@ class HTMLPurifier_AttrValidator // initialize CurrentToken if necessary $current_token =& $context->get('CurrentToken', true); - if (!$current_token) $context->register('CurrentToken', $token); + if (!$current_token) { + $context->register('CurrentToken', $token); + } - if ( - !$token instanceof HTMLPurifier_Token_Start && + if (!$token instanceof HTMLPurifier_Token_Start && !$token instanceof HTMLPurifier_Token_Empty - ) return $token; + ) { + return; + } // create alias to global definition array, see also $defs // DEFINITION CALL @@ -51,7 +51,9 @@ class HTMLPurifier_AttrValidator foreach ($definition->info_attr_transform_pre as $transform) { $attr = $transform->transform($o = $attr, $config, $context); if ($e) { - if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } } } @@ -60,7 +62,9 @@ class HTMLPurifier_AttrValidator foreach ($definition->info[$token->name]->attr_transform_pre as $transform) { $attr = $transform->transform($o = $attr, $config, $context); if ($e) { - if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } } } @@ -77,7 +81,7 @@ class HTMLPurifier_AttrValidator foreach ($attr as $attr_key => $value) { // call the definition - if ( isset($defs[$attr_key]) ) { + if (isset($defs[$attr_key])) { // there is a local definition defined if ($defs[$attr_key] === false) { // We've explicitly been told not to allow this element. @@ -89,15 +93,19 @@ class HTMLPurifier_AttrValidator } else { // validate according to the element's definition $result = $defs[$attr_key]->validate( - $value, $config, $context - ); + $value, + $config, + $context + ); } - } elseif ( isset($d_defs[$attr_key]) ) { + } elseif (isset($d_defs[$attr_key])) { // there is a global definition defined, validate according // to the global definition $result = $d_defs[$attr_key]->validate( - $value, $config, $context - ); + $value, + $config, + $context + ); } else { // system never heard of the attribute? DELETE! $result = false; @@ -107,7 +115,9 @@ class HTMLPurifier_AttrValidator if ($result === false || $result === null) { // this is a generic error message that should replaced // with more specific ones when possible - if ($e) $e->send(E_ERROR, 'AttrValidator: Attribute removed'); + if ($e) { + $e->send(E_ERROR, 'AttrValidator: Attribute removed'); + } // remove the attribute unset($attr[$attr_key]); @@ -137,7 +147,9 @@ class HTMLPurifier_AttrValidator foreach ($definition->info_attr_transform_post as $transform) { $attr = $transform->transform($o = $attr, $config, $context); if ($e) { - if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } } } @@ -145,14 +157,18 @@ class HTMLPurifier_AttrValidator foreach ($definition->info[$token->name]->attr_transform_post as $transform) { $attr = $transform->transform($o = $attr, $config, $context); if ($e) { - if ($attr != $o) $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + if ($attr != $o) { + $e->send(E_NOTICE, 'AttrValidator: Attributes transformed', $o, $attr); + } } } $token->attr = $attr; // destroy CurrentToken if we made it ourselves - if (!$current_token) $context->destroy('CurrentToken'); + if (!$current_token) { + $context->destroy('CurrentToken'); + } } diff --git a/library/HTMLPurifier/Bootstrap.php b/library/HTMLPurifier/Bootstrap.php index 559f61a23..707122bb2 100644 --- a/library/HTMLPurifier/Bootstrap.php +++ b/library/HTMLPurifier/Bootstrap.php @@ -32,20 +32,34 @@ class HTMLPurifier_Bootstrap /** * Autoload function for HTML Purifier - * @param $class Class to load + * @param string $class Class to load + * @return bool */ - public static function autoload($class) { + public static function autoload($class) + { $file = HTMLPurifier_Bootstrap::getPath($class); - if (!$file) return false; - require HTMLPURIFIER_PREFIX . '/' . $file; + if (!$file) { + return false; + } + // Technically speaking, it should be ok and more efficient to + // just do 'require', but Antonio Parraga reports that with + // Zend extensions such as Zend debugger and APC, this invariant + // may be broken. Since we have efficient alternatives, pay + // the cost here and avoid the bug. + require_once HTMLPURIFIER_PREFIX . '/' . $file; return true; } /** * Returns the path for a specific class. + * @param string $class Class path to get + * @return string */ - public static function getPath($class) { - if (strncmp('HTMLPurifier', $class, 12) !== 0) return false; + public static function getPath($class) + { + if (strncmp('HTMLPurifier', $class, 12) !== 0) { + return false; + } // Custom implementations if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) { $code = str_replace('_', '-', substr($class, 22)); @@ -53,46 +67,58 @@ class HTMLPurifier_Bootstrap } else { $file = str_replace('_', '/', $class) . '.php'; } - if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) return false; + if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) { + return false; + } return $file; } /** * "Pre-registers" our autoloader on the SPL stack. */ - public static function registerAutoload() { + public static function registerAutoload() + { $autoload = array('HTMLPurifier_Bootstrap', 'autoload'); - if ( ($funcs = spl_autoload_functions()) === false ) { + if (($funcs = spl_autoload_functions()) === false) { spl_autoload_register($autoload); } elseif (function_exists('spl_autoload_unregister')) { - $compat = version_compare(PHP_VERSION, '5.1.2', '<=') && - version_compare(PHP_VERSION, '5.1.0', '>='); - foreach ($funcs as $func) { - if (is_array($func)) { - // :TRICKY: There are some compatibility issues and some - // places where we need to error out - $reflector = new ReflectionMethod($func[0], $func[1]); - if (!$reflector->isStatic()) { - throw new Exception(' - HTML Purifier autoloader registrar is not compatible - with non-static object methods due to PHP Bug #44144; - Please do not use HTMLPurifier.autoload.php (or any - file that includes this file); instead, place the code: - spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\')) - after your own autoloaders. - '); + if (version_compare(PHP_VERSION, '5.3.0', '>=')) { + // prepend flag exists, no need for shenanigans + spl_autoload_register($autoload, true, true); + } else { + $buggy = version_compare(PHP_VERSION, '5.2.11', '<'); + $compat = version_compare(PHP_VERSION, '5.1.2', '<=') && + version_compare(PHP_VERSION, '5.1.0', '>='); + foreach ($funcs as $func) { + if ($buggy && is_array($func)) { + // :TRICKY: There are some compatibility issues and some + // places where we need to error out + $reflector = new ReflectionMethod($func[0], $func[1]); + if (!$reflector->isStatic()) { + throw new Exception( + 'HTML Purifier autoloader registrar is not compatible + with non-static object methods due to PHP Bug #44144; + Please do not use HTMLPurifier.autoload.php (or any + file that includes this file); instead, place the code: + spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\')) + after your own autoloaders.' + ); + } + // Suprisingly, spl_autoload_register supports the + // Class::staticMethod callback format, although call_user_func doesn't + if ($compat) { + $func = implode('::', $func); + } } - // Suprisingly, spl_autoload_register supports the - // Class::staticMethod callback format, although call_user_func doesn't - if ($compat) $func = implode('::', $func); + spl_autoload_unregister($func); + } + spl_autoload_register($autoload); + foreach ($funcs as $func) { + spl_autoload_register($func); } - spl_autoload_unregister($func); } - spl_autoload_register($autoload); - foreach ($funcs as $func) spl_autoload_register($func); } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/CSSDefinition.php b/library/HTMLPurifier/CSSDefinition.php index 6a2e6f56d..0acdee2d9 100644 --- a/library/HTMLPurifier/CSSDefinition.php +++ b/library/HTMLPurifier/CSSDefinition.php @@ -11,35 +11,59 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition /** * Assoc array of attribute name to definition object. + * @type HTMLPurifier_AttrDef[] */ public $info = array(); /** * Constructs the info array. The meat of this class. + * @param HTMLPurifier_Config $config */ - protected function doSetup($config) { - + protected function doSetup($config) + { $this->info['text-align'] = new HTMLPurifier_AttrDef_Enum( - array('left', 'right', 'center', 'justify'), false); + array('left', 'right', 'center', 'justify'), + false + ); $border_style = - $this->info['border-bottom-style'] = - $this->info['border-right-style'] = - $this->info['border-left-style'] = - $this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum( - array('none', 'hidden', 'dotted', 'dashed', 'solid', 'double', - 'groove', 'ridge', 'inset', 'outset'), false); + $this->info['border-bottom-style'] = + $this->info['border-right-style'] = + $this->info['border-left-style'] = + $this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum( + array( + 'none', + 'hidden', + 'dotted', + 'dashed', + 'solid', + 'double', + 'groove', + 'ridge', + 'inset', + 'outset' + ), + false + ); $this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style); $this->info['clear'] = new HTMLPurifier_AttrDef_Enum( - array('none', 'left', 'right', 'both'), false); + array('none', 'left', 'right', 'both'), + false + ); $this->info['float'] = new HTMLPurifier_AttrDef_Enum( - array('none', 'left', 'right'), false); + array('none', 'left', 'right'), + false + ); $this->info['font-style'] = new HTMLPurifier_AttrDef_Enum( - array('normal', 'italic', 'oblique'), false); + array('normal', 'italic', 'oblique'), + false + ); $this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum( - array('normal', 'small-caps'), false); + array('normal', 'small-caps'), + false + ); $uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite( array( @@ -49,16 +73,31 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition ); $this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum( - array('inside', 'outside'), false); + array('inside', 'outside'), + false + ); $this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum( - array('disc', 'circle', 'square', 'decimal', 'lower-roman', - 'upper-roman', 'lower-alpha', 'upper-alpha', 'none'), false); + array( + 'disc', + 'circle', + 'square', + 'decimal', + 'lower-roman', + 'upper-roman', + 'lower-alpha', + 'upper-alpha', + 'none' + ), + false + ); $this->info['list-style-image'] = $uri_or_none; $this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config); $this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum( - array('capitalize', 'uppercase', 'lowercase', 'none'), false); + array('capitalize', 'uppercase', 'lowercase', 'none'), + false + ); $this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color(); $this->info['background-image'] = $uri_or_none; @@ -71,104 +110,137 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition $this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition(); $border_color = - $this->info['border-top-color'] = - $this->info['border-bottom-color'] = - $this->info['border-left-color'] = - $this->info['border-right-color'] = - $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('transparent')), - new HTMLPurifier_AttrDef_CSS_Color() - )); + $this->info['border-top-color'] = + $this->info['border-bottom-color'] = + $this->info['border-left-color'] = + $this->info['border-right-color'] = + $this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('transparent')), + new HTMLPurifier_AttrDef_CSS_Color() + ) + ); $this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config); $this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color); $border_width = - $this->info['border-top-width'] = - $this->info['border-bottom-width'] = - $this->info['border-left-width'] = - $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')), - new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative - )); + $this->info['border-top-width'] = + $this->info['border-bottom-width'] = + $this->info['border-left-width'] = + $this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')), + new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative + ) + ); $this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width); - $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('normal')), - new HTMLPurifier_AttrDef_CSS_Length() - )); - - $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('normal')), - new HTMLPurifier_AttrDef_CSS_Length() - )); - - $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('xx-small', 'x-small', - 'small', 'medium', 'large', 'x-large', 'xx-large', - 'larger', 'smaller')), - new HTMLPurifier_AttrDef_CSS_Percentage(), - new HTMLPurifier_AttrDef_CSS_Length() - )); - - $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('normal')), - new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives - new HTMLPurifier_AttrDef_CSS_Length('0'), - new HTMLPurifier_AttrDef_CSS_Percentage(true) - )); + $this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'xx-small', + 'x-small', + 'small', + 'medium', + 'large', + 'x-large', + 'xx-large', + 'larger', + 'smaller' + ) + ), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_CSS_Length() + ) + ); + + $this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum(array('normal')), + new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true) + ) + ); $margin = - $this->info['margin-top'] = - $this->info['margin-bottom'] = - $this->info['margin-left'] = - $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage(), - new HTMLPurifier_AttrDef_Enum(array('auto')) - )); + $this->info['margin-top'] = + $this->info['margin-bottom'] = + $this->info['margin-left'] = + $this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ); $this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin); // non-negative $padding = - $this->info['padding-top'] = - $this->info['padding-bottom'] = - $this->info['padding-left'] = - $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_CSS_Length('0'), - new HTMLPurifier_AttrDef_CSS_Percentage(true) - )); + $this->info['padding-top'] = + $this->info['padding-bottom'] = + $this->info['padding-left'] = + $this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true) + ) + ); $this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding); - $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage() - )); + $this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage() + ) + ); - $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_CSS_Length('0'), - new HTMLPurifier_AttrDef_CSS_Percentage(true), - new HTMLPurifier_AttrDef_Enum(array('auto')) - )); + $trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0'), + new HTMLPurifier_AttrDef_CSS_Percentage(true), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ); $max = $config->get('CSS.MaxImgLength'); $this->info['width'] = $this->info['height'] = $max === null ? - $trusted_wh : - new HTMLPurifier_AttrDef_Switch('img', - // For img tags: - new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_CSS_Length('0', $max), - new HTMLPurifier_AttrDef_Enum(array('auto')) - )), - // For everyone else: - $trusted_wh - ); + $trusted_wh : + new HTMLPurifier_AttrDef_Switch( + 'img', + // For img tags: + new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length('0', $max), + new HTMLPurifier_AttrDef_Enum(array('auto')) + ) + ), + // For everyone else: + $trusted_wh + ); $this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration(); @@ -176,8 +248,23 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition // this could use specialized code $this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum( - array('normal', 'bold', 'bolder', 'lighter', '100', '200', '300', - '400', '500', '600', '700', '800', '900'), false); + array( + 'normal', + 'bold', + 'bolder', + 'lighter', + '100', + '200', + '300', + '400', + '500', + '600', + '700', + '800', + '900' + ), + false + ); // MUST be called after other font properties, as it references // a CSSDefinition object @@ -190,26 +277,44 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition $this->info['border-left'] = $this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config); - $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array( - 'collapse', 'separate')); + $this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum( + array('collapse', 'separate') + ); - $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(array( - 'top', 'bottom')); + $this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum( + array('top', 'bottom') + ); - $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum(array( - 'auto', 'fixed')); + $this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum( + array('auto', 'fixed') + ); - $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite(array( - new HTMLPurifier_AttrDef_Enum(array('baseline', 'sub', 'super', - 'top', 'text-top', 'middle', 'bottom', 'text-bottom')), - new HTMLPurifier_AttrDef_CSS_Length(), - new HTMLPurifier_AttrDef_CSS_Percentage() - )); + $this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Enum( + array( + 'baseline', + 'sub', + 'super', + 'top', + 'text-top', + 'middle', + 'bottom', + 'text-bottom' + ) + ), + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage() + ) + ); $this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2); - // partial support - $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap')); + // These CSS properties don't work on many browsers, but we live + // in THE FUTURE! + $this->info['white-space'] = new HTMLPurifier_AttrDef_Enum( + array('nowrap', 'normal', 'pre', 'pre-wrap', 'pre-line') + ); if ($config->get('CSS.Proprietary')) { $this->doSetupProprietary($config); @@ -219,6 +324,10 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition $this->doSetupTricky($config); } + if ($config->get('CSS.Trusted')) { + $this->doSetupTrusted($config); + } + $allow_important = $config->get('CSS.AllowImportant'); // wrap all attr-defs with decorator that handles !important foreach ($this->info as $k => $v) { @@ -228,64 +337,137 @@ class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition $this->setupConfigStuff($config); } - protected function doSetupProprietary($config) { + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupProprietary($config) + { // Internet Explorer only scrollbar colors - $this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color(); - $this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color(); + $this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color(); // technically not proprietary, but CSS3, and no one supports it - $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); - $this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); - $this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + $this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + $this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); + $this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue(); // only opacity, for now $this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter(); + // more CSS3 + $this->info['page-break-after'] = + $this->info['page-break-before'] = new HTMLPurifier_AttrDef_Enum( + array( + 'auto', + 'always', + 'avoid', + 'left', + 'right' + ) + ); + $this->info['page-break-inside'] = new HTMLPurifier_AttrDef_Enum(array('auto', 'avoid')); + } - protected function doSetupTricky($config) { - $this->info['display'] = new HTMLPurifier_AttrDef_Enum(array( - 'inline', 'block', 'list-item', 'run-in', 'compact', - 'marker', 'table', 'inline-table', 'table-row-group', - 'table-header-group', 'table-footer-group', 'table-row', - 'table-column-group', 'table-column', 'table-cell', 'table-caption', 'none' - )); - $this->info['visibility'] = new HTMLPurifier_AttrDef_Enum(array( - 'visible', 'hidden', 'collapse' - )); + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTricky($config) + { + $this->info['display'] = new HTMLPurifier_AttrDef_Enum( + array( + 'inline', + 'block', + 'list-item', + 'run-in', + 'compact', + 'marker', + 'table', + 'inline-block', + 'inline-table', + 'table-row-group', + 'table-header-group', + 'table-footer-group', + 'table-row', + 'table-column-group', + 'table-column', + 'table-cell', + 'table-caption', + 'none' + ) + ); + $this->info['visibility'] = new HTMLPurifier_AttrDef_Enum( + array('visible', 'hidden', 'collapse') + ); $this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll')); } + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetupTrusted($config) + { + $this->info['position'] = new HTMLPurifier_AttrDef_Enum( + array('static', 'relative', 'absolute', 'fixed') + ); + $this->info['top'] = + $this->info['left'] = + $this->info['right'] = + $this->info['bottom'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_CSS_Length(), + new HTMLPurifier_AttrDef_CSS_Percentage(), + new HTMLPurifier_AttrDef_Enum(array('auto')), + ) + ); + $this->info['z-index'] = new HTMLPurifier_AttrDef_CSS_Composite( + array( + new HTMLPurifier_AttrDef_Integer(), + new HTMLPurifier_AttrDef_Enum(array('auto')), + ) + ); + } /** * Performs extra config-based processing. Based off of * HTMLPurifier_HTMLDefinition. + * @param HTMLPurifier_Config $config * @todo Refactor duplicate elements into common class (probably using * composition, not inheritance). */ - protected function setupConfigStuff($config) { - + protected function setupConfigStuff($config) + { // setup allowed elements - $support = "(for information on implementing this, see the ". - "support forums) "; - $allowed_attributes = $config->get('CSS.AllowedProperties'); - if ($allowed_attributes !== null) { + $support = "(for information on implementing this, see the " . + "support forums) "; + $allowed_properties = $config->get('CSS.AllowedProperties'); + if ($allowed_properties !== null) { foreach ($this->info as $name => $d) { - if(!isset($allowed_attributes[$name])) unset($this->info[$name]); - unset($allowed_attributes[$name]); + if (!isset($allowed_properties[$name])) { + unset($this->info[$name]); + } + unset($allowed_properties[$name]); } // emit errors - foreach ($allowed_attributes as $name => $d) { + foreach ($allowed_properties as $name => $d) { // :TODO: Is this htmlspecialchars() call really necessary? $name = htmlspecialchars($name); trigger_error("Style attribute '$name' is not supported $support", E_USER_WARNING); } } + $forbidden_properties = $config->get('CSS.ForbiddenProperties'); + if ($forbidden_properties !== null) { + foreach ($this->info as $name => $d) { + if (isset($forbidden_properties[$name])) { + unset($this->info[$name]); + } + } + } } } diff --git a/library/HTMLPurifier/ChildDef.php b/library/HTMLPurifier/ChildDef.php index c5d5216da..8eb17b82e 100644 --- a/library/HTMLPurifier/ChildDef.php +++ b/library/HTMLPurifier/ChildDef.php @@ -1,48 +1,52 @@ <?php /** - * Defines allowed child nodes and validates tokens against it. + * Defines allowed child nodes and validates nodes against it. */ abstract class HTMLPurifier_ChildDef { /** * Type of child definition, usually right-most part of class name lowercase. * Used occasionally in terms of context. + * @type string */ public $type; /** - * Bool that indicates whether or not an empty array of children is okay + * Indicates whether or not an empty array of children is okay. * * This is necessary for redundant checking when changes affecting * a child node may cause a parent node to now be disallowed. + * @type bool */ public $allow_empty; /** - * Lookup array of all elements that this definition could possibly allow + * Lookup array of all elements that this definition could possibly allow. + * @type array */ public $elements = array(); /** * Get lookup of tag names that should not close this element automatically. * All other elements will do so. + * @param HTMLPurifier_Config $config HTMLPurifier_Config object + * @return array */ - public function getAllowedElements($config) { + public function getAllowedElements($config) + { return $this->elements; } /** * Validates nodes according to definition and returns modification. * - * @param $tokens_of_children Array of HTMLPurifier_Token - * @param $config HTMLPurifier_Config object - * @param $context HTMLPurifier_Context object - * @return bool true to leave nodes as is - * @return bool false to remove parent node - * @return array of replacement child tokens + * @param HTMLPurifier_Node[] $children Array of HTMLPurifier_Node + * @param HTMLPurifier_Config $config HTMLPurifier_Config object + * @param HTMLPurifier_Context $context HTMLPurifier_Context object + * @return bool|array true to leave nodes as is, false to remove parent node, array of replacement children */ - abstract public function validateChildren($tokens_of_children, $config, $context); + abstract public function validateChildren($children, $config, $context); } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ChildDef/Chameleon.php b/library/HTMLPurifier/ChildDef/Chameleon.php index 15c364ee3..7439be26b 100644 --- a/library/HTMLPurifier/ChildDef/Chameleon.php +++ b/library/HTMLPurifier/ChildDef/Chameleon.php @@ -14,33 +14,52 @@ class HTMLPurifier_ChildDef_Chameleon extends HTMLPurifier_ChildDef /** * Instance of the definition object to use when inline. Usually stricter. + * @type HTMLPurifier_ChildDef_Optional */ public $inline; /** * Instance of the definition object to use when block. + * @type HTMLPurifier_ChildDef_Optional */ public $block; + /** + * @type string + */ public $type = 'chameleon'; /** - * @param $inline List of elements to allow when inline. - * @param $block List of elements to allow when block. + * @param array $inline List of elements to allow when inline. + * @param array $block List of elements to allow when block. */ - public function __construct($inline, $block) { + public function __construct($inline, $block) + { $this->inline = new HTMLPurifier_ChildDef_Optional($inline); - $this->block = new HTMLPurifier_ChildDef_Optional($block); + $this->block = new HTMLPurifier_ChildDef_Optional($block); $this->elements = $this->block->elements; } - public function validateChildren($tokens_of_children, $config, $context) { + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { if ($context->get('IsInline') === false) { return $this->block->validateChildren( - $tokens_of_children, $config, $context); + $children, + $config, + $context + ); } else { return $this->inline->validateChildren( - $tokens_of_children, $config, $context); + $children, + $config, + $context + ); } } } diff --git a/library/HTMLPurifier/ChildDef/Custom.php b/library/HTMLPurifier/ChildDef/Custom.php index b68047b4b..128132e96 100644 --- a/library/HTMLPurifier/ChildDef/Custom.php +++ b/library/HTMLPurifier/ChildDef/Custom.php @@ -8,28 +8,42 @@ */ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef { + /** + * @type string + */ public $type = 'custom'; + + /** + * @type bool + */ public $allow_empty = false; + /** - * Allowed child pattern as defined by the DTD + * Allowed child pattern as defined by the DTD. + * @type string */ public $dtd_regex; + /** - * PCRE regex derived from $dtd_regex - * @private + * PCRE regex derived from $dtd_regex. + * @type string */ private $_pcre_regex; + /** * @param $dtd_regex Allowed child pattern from the DTD */ - public function __construct($dtd_regex) { + public function __construct($dtd_regex) + { $this->dtd_regex = $dtd_regex; $this->_compileRegex(); } + /** * Compiles the PCRE regex from a DTD regex ($dtd_regex to $_pcre_regex) */ - protected function _compileRegex() { + protected function _compileRegex() + { $raw = str_replace(' ', '', $this->dtd_regex); if ($raw{0} != '(') { $raw = "($raw)"; @@ -57,33 +71,31 @@ class HTMLPurifier_ChildDef_Custom extends HTMLPurifier_ChildDef $this->_pcre_regex = $reg; } - public function validateChildren($tokens_of_children, $config, $context) { + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function validateChildren($children, $config, $context) + { $list_of_children = ''; $nesting = 0; // depth into the nest - foreach ($tokens_of_children as $token) { - if (!empty($token->is_whitespace)) continue; - - $is_child = ($nesting == 0); // direct - - if ($token instanceof HTMLPurifier_Token_Start) { - $nesting++; - } elseif ($token instanceof HTMLPurifier_Token_End) { - $nesting--; - } - - if ($is_child) { - $list_of_children .= $token->name . ','; + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + continue; } + $list_of_children .= $node->name . ','; } // add leading comma to deal with stray comma declarations $list_of_children = ',' . rtrim($list_of_children, ','); $okay = preg_match( - '/^,?'.$this->_pcre_regex.'$/', + '/^,?' . $this->_pcre_regex . '$/', $list_of_children ); - - return (bool) $okay; + return (bool)$okay; } } diff --git a/library/HTMLPurifier/ChildDef/Empty.php b/library/HTMLPurifier/ChildDef/Empty.php index 13171f665..a8a6cbdd2 100644 --- a/library/HTMLPurifier/ChildDef/Empty.php +++ b/library/HTMLPurifier/ChildDef/Empty.php @@ -9,10 +9,28 @@ */ class HTMLPurifier_ChildDef_Empty extends HTMLPurifier_ChildDef { + /** + * @type bool + */ public $allow_empty = true; + + /** + * @type string + */ public $type = 'empty'; - public function __construct() {} - public function validateChildren($tokens_of_children, $config, $context) { + + public function __construct() + { + } + + /** + * @param HTMLPurifier_Node[] $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { return array(); } } diff --git a/library/HTMLPurifier/ChildDef/List.php b/library/HTMLPurifier/ChildDef/List.php new file mode 100644 index 000000000..891b9f6f5 --- /dev/null +++ b/library/HTMLPurifier/ChildDef/List.php @@ -0,0 +1,86 @@ +<?php + +/** + * Definition for list containers ul and ol. + * + * What does this do? The big thing is to handle ol/ul at the top + * level of list nodes, which should be handled specially by /folding/ + * them into the previous list node. We generally shouldn't ever + * see other disallowed elements, because the autoclose behavior + * in MakeWellFormed handles it. + */ +class HTMLPurifier_ChildDef_List extends HTMLPurifier_ChildDef +{ + /** + * @type string + */ + public $type = 'list'; + /** + * @type array + */ + // lying a little bit, so that we can handle ul and ol ourselves + // XXX: This whole business with 'wrap' is all a bit unsatisfactory + public $elements = array('li' => true, 'ul' => true, 'ol' => true); + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + // Flag for subclasses + $this->whitespace = false; + + // if there are no tokens, delete parent node + if (empty($children)) { + return false; + } + + // the new set of children + $result = array(); + + // a little sanity check to make sure it's not ALL whitespace + $all_whitespace = true; + + $current_li = false; + + foreach ($children as $node) { + if (!empty($node->is_whitespace)) { + $result[] = $node; + continue; + } + $all_whitespace = false; // phew, we're not talking about whitespace + + if ($node->name === 'li') { + // good + $current_li = $node; + $result[] = $node; + } else { + // we want to tuck this into the previous li + // Invariant: we expect the node to be ol/ul + // ToDo: Make this more robust in the case of not ol/ul + // by distinguishing between existing li and li created + // to handle non-list elements; non-list elements should + // not be appended to an existing li; only li created + // for non-list. This distinction is not currently made. + if ($current_li === false) { + $current_li = new HTMLPurifier_Node_Element('li'); + $result[] = $current_li; + } + $current_li->children[] = $node; + $current_li->empty = false; // XXX fascinating! Check for this error elsewhere ToDo + } + } + if (empty($result)) { + return false; + } + if ($all_whitespace) { + return false; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ChildDef/Optional.php b/library/HTMLPurifier/ChildDef/Optional.php index 32bcb9898..b9468063b 100644 --- a/library/HTMLPurifier/ChildDef/Optional.php +++ b/library/HTMLPurifier/ChildDef/Optional.php @@ -9,15 +9,34 @@ */ class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required { + /** + * @type bool + */ public $allow_empty = true; + + /** + * @type string + */ public $type = 'optional'; - public function validateChildren($tokens_of_children, $config, $context) { - $result = parent::validateChildren($tokens_of_children, $config, $context); - // we assume that $tokens_of_children is not modified + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + $result = parent::validateChildren($children, $config, $context); + // we assume that $children is not modified if ($result === false) { - if (empty($tokens_of_children)) return true; - elseif ($this->whitespace) return $tokens_of_children; - else return array(); + if (empty($children)) { + return true; + } elseif ($this->whitespace) { + return $children; + } else { + return array(); + } } return $result; } diff --git a/library/HTMLPurifier/ChildDef/Required.php b/library/HTMLPurifier/ChildDef/Required.php index 4889f249b..0d1c8f5f3 100644 --- a/library/HTMLPurifier/ChildDef/Required.php +++ b/library/HTMLPurifier/ChildDef/Required.php @@ -7,17 +7,21 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef { /** * Lookup table of allowed elements. - * @public + * @type array */ public $elements = array(); + /** * Whether or not the last passed node was all whitespace. + * @type bool */ protected $whitespace = false; + /** - * @param $elements List of allowed element names (lowercase). + * @param array|string $elements List of allowed element names (lowercase). */ - public function __construct($elements) { + public function __construct($elements) + { if (is_string($elements)) { $elements = str_replace(' ', '', $elements); $elements = explode('|', $elements); @@ -27,29 +31,43 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef $elements = array_flip($elements); foreach ($elements as $i => $x) { $elements[$i] = true; - if (empty($i)) unset($elements[$i]); // remove blank + if (empty($i)) { + unset($elements[$i]); + } // remove blank } } $this->elements = $elements; } + + /** + * @type bool + */ public $allow_empty = false; + + /** + * @type string + */ public $type = 'required'; - public function validateChildren($tokens_of_children, $config, $context) { + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { // Flag for subclasses $this->whitespace = false; // if there are no tokens, delete parent node - if (empty($tokens_of_children)) return false; + if (empty($children)) { + return false; + } // the new set of children $result = array(); - // current depth into the nest - $nesting = 0; - - // whether or not we're deleting a node - $is_deleting = false; - // whether or not parsed character data is allowed // this controls whether or not we silently drop a tag // or generate escaped HTML from it @@ -58,58 +76,41 @@ class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef // a little sanity check to make sure it's not ALL whitespace $all_whitespace = true; - // some configuration - $escape_invalid_children = $config->get('Core.EscapeInvalidChildren'); - - // generator - $gen = new HTMLPurifier_Generator($config, $context); - - foreach ($tokens_of_children as $token) { - if (!empty($token->is_whitespace)) { - $result[] = $token; + $stack = array_reverse($children); + while (!empty($stack)) { + $node = array_pop($stack); + if (!empty($node->is_whitespace)) { + $result[] = $node; continue; } $all_whitespace = false; // phew, we're not talking about whitespace - $is_child = ($nesting == 0); - - if ($token instanceof HTMLPurifier_Token_Start) { - $nesting++; - } elseif ($token instanceof HTMLPurifier_Token_End) { - $nesting--; - } - - if ($is_child) { - $is_deleting = false; - if (!isset($this->elements[$token->name])) { - $is_deleting = true; - if ($pcdata_allowed && $token instanceof HTMLPurifier_Token_Text) { - $result[] = $token; - } elseif ($pcdata_allowed && $escape_invalid_children) { - $result[] = new HTMLPurifier_Token_Text( - $gen->generateFromToken($token) - ); + if (!isset($this->elements[$node->name])) { + // special case text + // XXX One of these ought to be redundant or something + if ($pcdata_allowed && $node instanceof HTMLPurifier_Node_Text) { + $result[] = $node; + continue; + } + // spill the child contents in + // ToDo: Make configurable + if ($node instanceof HTMLPurifier_Node_Element) { + for ($i = count($node->children) - 1; $i >= 0; $i--) { + $stack[] = $node->children[$i]; } continue; } + continue; } - if (!$is_deleting || ($pcdata_allowed && $token instanceof HTMLPurifier_Token_Text)) { - $result[] = $token; - } elseif ($pcdata_allowed && $escape_invalid_children) { - $result[] = - new HTMLPurifier_Token_Text( - $gen->generateFromToken($token) - ); - } else { - // drop silently - } + $result[] = $node; + } + if (empty($result)) { + return false; } - if (empty($result)) return false; if ($all_whitespace) { $this->whitespace = true; return false; } - if ($tokens_of_children == $result) return true; return $result; } } diff --git a/library/HTMLPurifier/ChildDef/StrictBlockquote.php b/library/HTMLPurifier/ChildDef/StrictBlockquote.php index dfae8a6e5..3270a46e1 100644 --- a/library/HTMLPurifier/ChildDef/StrictBlockquote.php +++ b/library/HTMLPurifier/ChildDef/StrictBlockquote.php @@ -5,75 +5,97 @@ */ class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Required { + /** + * @type array + */ protected $real_elements; + + /** + * @type array + */ protected $fake_elements; + + /** + * @type bool + */ public $allow_empty = true; + + /** + * @type string + */ public $type = 'strictblockquote'; + + /** + * @type bool + */ protected $init = false; /** + * @param HTMLPurifier_Config $config + * @return array * @note We don't want MakeWellFormed to auto-close inline elements since * they might be allowed. */ - public function getAllowedElements($config) { + public function getAllowedElements($config) + { $this->init($config); return $this->fake_elements; } - public function validateChildren($tokens_of_children, $config, $context) { - + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { $this->init($config); // trick the parent class into thinking it allows more $this->elements = $this->fake_elements; - $result = parent::validateChildren($tokens_of_children, $config, $context); + $result = parent::validateChildren($children, $config, $context); $this->elements = $this->real_elements; - if ($result === false) return array(); - if ($result === true) $result = $tokens_of_children; + if ($result === false) { + return array(); + } + if ($result === true) { + $result = $children; + } $def = $config->getHTMLDefinition(); - $block_wrap_start = new HTMLPurifier_Token_Start($def->info_block_wrapper); - $block_wrap_end = new HTMLPurifier_Token_End( $def->info_block_wrapper); - $is_inline = false; - $depth = 0; + $block_wrap_name = $def->info_block_wrapper; + $block_wrap = false; $ret = array(); - // assuming that there are no comment tokens - foreach ($result as $i => $token) { - $token = $result[$i]; - // ifs are nested for readability - if (!$is_inline) { - if (!$depth) { - if ( - ($token instanceof HTMLPurifier_Token_Text && !$token->is_whitespace) || - (!$token instanceof HTMLPurifier_Token_Text && !isset($this->elements[$token->name])) - ) { - $is_inline = true; - $ret[] = $block_wrap_start; - } + foreach ($result as $node) { + if ($block_wrap === false) { + if (($node instanceof HTMLPurifier_Node_Text && !$node->is_whitespace) || + ($node instanceof HTMLPurifier_Node_Element && !isset($this->elements[$node->name]))) { + $block_wrap = new HTMLPurifier_Node_Element($def->info_block_wrapper); + $ret[] = $block_wrap; } } else { - if (!$depth) { - // starting tokens have been inline text / empty - if ($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) { - if (isset($this->elements[$token->name])) { - // ended - $ret[] = $block_wrap_end; - $is_inline = false; - } - } + if ($node instanceof HTMLPurifier_Node_Element && isset($this->elements[$node->name])) { + $block_wrap = false; + } } - $ret[] = $token; - if ($token instanceof HTMLPurifier_Token_Start) $depth++; - if ($token instanceof HTMLPurifier_Token_End) $depth--; + if ($block_wrap) { + $block_wrap->children[] = $node; + } else { + $ret[] = $node; + } } - if ($is_inline) $ret[] = $block_wrap_end; return $ret; } - private function init($config) { + /** + * @param HTMLPurifier_Config $config + */ + private function init($config) + { if (!$this->init) { $def = $config->getHTMLDefinition(); // allow all inline elements diff --git a/library/HTMLPurifier/ChildDef/Table.php b/library/HTMLPurifier/ChildDef/Table.php index 34f0227dd..3e4a0f218 100644 --- a/library/HTMLPurifier/ChildDef/Table.php +++ b/library/HTMLPurifier/ChildDef/Table.php @@ -1,140 +1,222 @@ <?php /** - * Definition for tables + * Definition for tables. The general idea is to extract out all of the + * essential bits, and then reconstruct it later. + * + * This is a bit confusing, because the DTDs and the W3C + * validators seem to disagree on the appropriate definition. The + * DTD claims: + * + * (CAPTION?, (COL*|COLGROUP*), THEAD?, TFOOT?, TBODY+) + * + * But actually, the HTML4 spec then has this to say: + * + * The TBODY start tag is always required except when the table + * contains only one table body and no table head or foot sections. + * The TBODY end tag may always be safely omitted. + * + * So the DTD is kind of wrong. The validator is, unfortunately, kind + * of on crack. + * + * The definition changed again in XHTML1.1; and in my opinion, this + * formulation makes the most sense. + * + * caption?, ( col* | colgroup* ), (( thead?, tfoot?, tbody+ ) | ( tr+ )) + * + * Essentially, we have two modes: thead/tfoot/tbody mode, and tr mode. + * If we encounter a thead, tfoot or tbody, we are placed in the former + * mode, and we *must* wrap any stray tr segments with a tbody. But if + * we don't run into any of them, just have tr tags is OK. */ class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef { + /** + * @type bool + */ public $allow_empty = false; + + /** + * @type string + */ public $type = 'table'; - public $elements = array('tr' => true, 'tbody' => true, 'thead' => true, - 'tfoot' => true, 'caption' => true, 'colgroup' => true, 'col' => true); - public function __construct() {} - public function validateChildren($tokens_of_children, $config, $context) { - if (empty($tokens_of_children)) return false; - // this ensures that the loop gets run one last time before closing - // up. It's a little bit of a hack, but it works! Just make sure you - // get rid of the token later. - $tokens_of_children[] = false; + /** + * @type array + */ + public $elements = array( + 'tr' => true, + 'tbody' => true, + 'thead' => true, + 'tfoot' => true, + 'caption' => true, + 'colgroup' => true, + 'col' => true + ); + + public function __construct() + { + } + + /** + * @param array $children + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array + */ + public function validateChildren($children, $config, $context) + { + if (empty($children)) { + return false; + } // only one of these elements is allowed in a table $caption = false; - $thead = false; - $tfoot = false; + $thead = false; + $tfoot = false; + + // whitespace + $initial_ws = array(); + $after_caption_ws = array(); + $after_thead_ws = array(); + $after_tfoot_ws = array(); // as many of these as you want - $cols = array(); + $cols = array(); $content = array(); - $nesting = 0; // current depth so we can determine nodes - $is_collecting = false; // are we globbing together tokens to package - // into one of the collectors? - $collection = array(); // collected nodes - $tag_index = 0; // the first node might be whitespace, - // so this tells us where the start tag is - - foreach ($tokens_of_children as $token) { - $is_child = ($nesting == 0); - - if ($token === false) { - // terminating sequence started - } elseif ($token instanceof HTMLPurifier_Token_Start) { - $nesting++; - } elseif ($token instanceof HTMLPurifier_Token_End) { - $nesting--; - } + $tbody_mode = false; // if true, then we need to wrap any stray + // <tr>s with a <tbody>. - // handle node collection - if ($is_collecting) { - if ($is_child) { - // okay, let's stash the tokens away - // first token tells us the type of the collection - switch ($collection[$tag_index]->name) { - case 'tr': - case 'tbody': - $content[] = $collection; - break; - case 'caption': - if ($caption !== false) break; - $caption = $collection; - break; - case 'thead': - case 'tfoot': - // access the appropriate variable, $thead or $tfoot - $var = $collection[$tag_index]->name; - if ($$var === false) { - $$var = $collection; - } else { - // transmutate the first and less entries into - // tbody tags, and then put into content - $collection[$tag_index]->name = 'tbody'; - $collection[count($collection)-1]->name = 'tbody'; - $content[] = $collection; - } - break; - case 'colgroup': - $cols[] = $collection; - break; - } - $collection = array(); - $is_collecting = false; - $tag_index = 0; + $ws_accum =& $initial_ws; + + foreach ($children as $node) { + if ($node instanceof HTMLPurifier_Node_Comment) { + $ws_accum[] = $node; + continue; + } + switch ($node->name) { + case 'tbody': + $tbody_mode = true; + // fall through + case 'tr': + $content[] = $node; + $ws_accum =& $content; + break; + case 'caption': + // there can only be one caption! + if ($caption !== false) break; + $caption = $node; + $ws_accum =& $after_caption_ws; + break; + case 'thead': + $tbody_mode = true; + // XXX This breaks rendering properties with + // Firefox, which never floats a <thead> to + // the top. Ever. (Our scheme will float the + // first <thead> to the top.) So maybe + // <thead>s that are not first should be + // turned into <tbody>? Very tricky, indeed. + if ($thead === false) { + $thead = $node; + $ws_accum =& $after_thead_ws; } else { - // add the node to the collection - $collection[] = $token; + // Oops, there's a second one! What + // should we do? Current behavior is to + // transmutate the first and last entries into + // tbody tags, and then put into content. + // Maybe a better idea is to *attach + // it* to the existing thead or tfoot? + // We don't do this, because Firefox + // doesn't float an extra tfoot to the + // bottom like it does for the first one. + $node->name = 'tbody'; + $content[] = $node; + $ws_accum =& $content; } - } - - // terminate - if ($token === false) break; - - if ($is_child) { - // determine what we're dealing with - if ($token->name == 'col') { - // the only empty tag in the possie, we can handle it - // immediately - $cols[] = array_merge($collection, array($token)); - $collection = array(); - $tag_index = 0; - continue; + break; + case 'tfoot': + // see above for some aveats + $tbody_mode = true; + if ($tfoot === false) { + $tfoot = $node; + $ws_accum =& $after_tfoot_ws; + } else { + $node->name = 'tbody'; + $content[] = $node; + $ws_accum =& $content; } - switch($token->name) { - case 'caption': - case 'colgroup': - case 'thead': - case 'tfoot': - case 'tbody': - case 'tr': - $is_collecting = true; - $collection[] = $token; - continue; - default: - if (!empty($token->is_whitespace)) { - $collection[] = $token; - $tag_index++; - } - continue; + break; + case 'colgroup': + case 'col': + $cols[] = $node; + $ws_accum =& $cols; + break; + case '#PCDATA': + // How is whitespace handled? We treat is as sticky to + // the *end* of the previous element. So all of the + // nonsense we have worked on is to keep things + // together. + if (!empty($node->is_whitespace)) { + $ws_accum[] = $node; } + break; } } - if (empty($content)) return false; - - $ret = array(); - if ($caption !== false) $ret = array_merge($ret, $caption); - if ($cols !== false) foreach ($cols as $token_array) $ret = array_merge($ret, $token_array); - if ($thead !== false) $ret = array_merge($ret, $thead); - if ($tfoot !== false) $ret = array_merge($ret, $tfoot); - foreach ($content as $token_array) $ret = array_merge($ret, $token_array); - if (!empty($collection) && $is_collecting == false){ - // grab the trailing space - $ret = array_merge($ret, $collection); + if (empty($content)) { + return false; + } + + $ret = $initial_ws; + if ($caption !== false) { + $ret[] = $caption; + $ret = array_merge($ret, $after_caption_ws); + } + if ($cols !== false) { + $ret = array_merge($ret, $cols); + } + if ($thead !== false) { + $ret[] = $thead; + $ret = array_merge($ret, $after_thead_ws); + } + if ($tfoot !== false) { + $ret[] = $tfoot; + $ret = array_merge($ret, $after_tfoot_ws); } - array_pop($tokens_of_children); // remove phantom token + if ($tbody_mode) { + // we have to shuffle tr into tbody + $current_tr_tbody = null; + + foreach($content as $node) { + switch ($node->name) { + case 'tbody': + $current_tr_tbody = null; + $ret[] = $node; + break; + case 'tr': + if ($current_tr_tbody === null) { + $current_tr_tbody = new HTMLPurifier_Node_Element('tbody'); + $ret[] = $current_tr_tbody; + } + $current_tr_tbody->children[] = $node; + break; + case '#PCDATA': + assert($node->is_whitespace); + if ($current_tr_tbody === null) { + $ret[] = $node; + } else { + $current_tr_tbody->children[] = $node; + } + break; + } + } + } else { + $ret = array_merge($ret, $content); + } - return ($ret === $tokens_of_children) ? true : $ret; + return $ret; } } diff --git a/library/HTMLPurifier/Config.php b/library/HTMLPurifier/Config.php index 2a334b0d8..7ada59b94 100644 --- a/library/HTMLPurifier/Config.php +++ b/library/HTMLPurifier/Config.php @@ -19,77 +19,92 @@ class HTMLPurifier_Config /** * HTML Purifier's version + * @type string */ - public $version = '4.1.1'; + public $version = '4.6.0'; /** - * Bool indicator whether or not to automatically finalize - * the object if a read operation is done + * Whether or not to automatically finalize + * the object if a read operation is done. + * @type bool */ public $autoFinalize = true; // protected member variables /** - * Namespace indexed array of serials for specific namespaces (see - * getSerial() for more info). + * Namespace indexed array of serials for specific namespaces. + * @see getSerial() for more info. + * @type string[] */ protected $serials = array(); /** - * Serial for entire configuration object + * Serial for entire configuration object. + * @type string */ protected $serial; /** - * Parser for variables + * Parser for variables. + * @type HTMLPurifier_VarParser_Flexible */ - protected $parser; + protected $parser = null; /** - * Reference HTMLPurifier_ConfigSchema for value checking + * Reference HTMLPurifier_ConfigSchema for value checking. + * @type HTMLPurifier_ConfigSchema * @note This is public for introspective purposes. Please don't * abuse! */ public $def; /** - * Indexed array of definitions + * Indexed array of definitions. + * @type HTMLPurifier_Definition[] */ protected $definitions; /** - * Bool indicator whether or not config is finalized + * Whether or not config is finalized. + * @type bool */ protected $finalized = false; /** * Property list containing configuration directives. + * @type array */ protected $plist; /** - * Whether or not a set is taking place due to an - * alias lookup. + * Whether or not a set is taking place due to an alias lookup. + * @type bool */ private $aliasMode; /** - * Set to false if you do not want line and file numbers in errors - * (useful when unit testing) + * Set to false if you do not want line and file numbers in errors. + * (useful when unit testing). This will also compress some errors + * and exceptions. + * @type bool */ public $chatty = true; /** * Current lock; only gets to this namespace are allowed. + * @type string */ private $lock; /** - * @param $definition HTMLPurifier_ConfigSchema that defines what directives - * are allowed. + * Constructor + * @param HTMLPurifier_ConfigSchema $definition ConfigSchema that defines + * what directives are allowed. + * @param HTMLPurifier_PropertyList $parent */ - public function __construct($definition, $parent = null) { + public function __construct($definition, $parent = null) + { $parent = $parent ? $parent : $definition->defaultPlist; $this->plist = new HTMLPurifier_PropertyList($parent); $this->def = $definition; // keep a copy around for checking @@ -102,10 +117,11 @@ class HTMLPurifier_Config * object. Can be: a HTMLPurifier_Config() object, * an array of directives based on loadArray(), * or a string filename of an ini file. - * @param HTMLPurifier_ConfigSchema Schema object - * @return Configured HTMLPurifier_Config object + * @param HTMLPurifier_ConfigSchema $schema Schema object + * @return HTMLPurifier_Config Configured object */ - public static function create($config, $schema = null) { + public static function create($config, $schema = null) + { if ($config instanceof HTMLPurifier_Config) { // pass-through return $config; @@ -115,57 +131,79 @@ class HTMLPurifier_Config } else { $ret = new HTMLPurifier_Config($schema); } - if (is_string($config)) $ret->loadIni($config); - elseif (is_array($config)) $ret->loadArray($config); + if (is_string($config)) { + $ret->loadIni($config); + } elseif (is_array($config)) $ret->loadArray($config); return $ret; } /** * Creates a new config object that inherits from a previous one. - * @param HTMLPurifier_Config $config Configuration object to inherit - * from. + * @param HTMLPurifier_Config $config Configuration object to inherit from. * @return HTMLPurifier_Config object with $config as its parent. */ - public static function inherit(HTMLPurifier_Config $config) { + public static function inherit(HTMLPurifier_Config $config) + { return new HTMLPurifier_Config($config->def, $config->plist); } /** * Convenience constructor that creates a default configuration object. - * @return Default HTMLPurifier_Config object. + * @return HTMLPurifier_Config default object. */ - public static function createDefault() { + public static function createDefault() + { $definition = HTMLPurifier_ConfigSchema::instance(); $config = new HTMLPurifier_Config($definition); return $config; } /** - * Retreives a value from the configuration. - * @param $key String key + * Retrieves a value from the configuration. + * + * @param string $key String key + * @param mixed $a + * + * @return mixed */ - public function get($key, $a = null) { + public function get($key, $a = null) + { if ($a !== null) { - $this->triggerError("Using deprecated API: use \$config->get('$key.$a') instead", E_USER_WARNING); + $this->triggerError( + "Using deprecated API: use \$config->get('$key.$a') instead", + E_USER_WARNING + ); $key = "$key.$a"; } - if (!$this->finalized) $this->autoFinalize(); + if (!$this->finalized) { + $this->autoFinalize(); + } if (!isset($this->def->info[$key])) { // can't add % due to SimpleTest bug - $this->triggerError('Cannot retrieve value of undefined directive ' . htmlspecialchars($key), - E_USER_WARNING); + $this->triggerError( + 'Cannot retrieve value of undefined directive ' . htmlspecialchars($key), + E_USER_WARNING + ); return; } if (isset($this->def->info[$key]->isAlias)) { $d = $this->def->info[$key]; - $this->triggerError('Cannot get value from aliased directive, use real name ' . $d->key, - E_USER_ERROR); + $this->triggerError( + 'Cannot get value from aliased directive, use real name ' . $d->key, + E_USER_ERROR + ); return; } if ($this->lock) { list($ns) = explode('.', $key); if ($ns !== $this->lock) { - $this->triggerError('Cannot get value of namespace ' . $ns . ' when lock for ' . $this->lock . ' is active, this probably indicates a Definition setup method is accessing directives that are not within its namespace', E_USER_ERROR); + $this->triggerError( + 'Cannot get value of namespace ' . $ns . ' when lock for ' . + $this->lock . + ' is active, this probably indicates a Definition setup method ' . + 'is accessing directives that are not within its namespace', + E_USER_ERROR + ); return; } } @@ -173,53 +211,73 @@ class HTMLPurifier_Config } /** - * Retreives an array of directives to values from a given namespace - * @param $namespace String namespace + * Retrieves an array of directives to values from a given namespace + * + * @param string $namespace String namespace + * + * @return array */ - public function getBatch($namespace) { - if (!$this->finalized) $this->autoFinalize(); + public function getBatch($namespace) + { + if (!$this->finalized) { + $this->autoFinalize(); + } $full = $this->getAll(); if (!isset($full[$namespace])) { - $this->triggerError('Cannot retrieve undefined namespace ' . htmlspecialchars($namespace), - E_USER_WARNING); + $this->triggerError( + 'Cannot retrieve undefined namespace ' . + htmlspecialchars($namespace), + E_USER_WARNING + ); return; } return $full[$namespace]; } /** - * Returns a md5 signature of a segment of the configuration object + * Returns a SHA-1 signature of a segment of the configuration object * that uniquely identifies that particular configuration + * + * @param string $namespace Namespace to get serial for + * + * @return string * @note Revision is handled specially and is removed from the batch * before processing! - * @param $namespace Namespace to get serial for */ - public function getBatchSerial($namespace) { + public function getBatchSerial($namespace) + { if (empty($this->serials[$namespace])) { $batch = $this->getBatch($namespace); unset($batch['DefinitionRev']); - $this->serials[$namespace] = md5(serialize($batch)); + $this->serials[$namespace] = sha1(serialize($batch)); } return $this->serials[$namespace]; } /** - * Returns a md5 signature for the entire configuration object + * Returns a SHA-1 signature for the entire configuration object * that uniquely identifies that particular configuration + * + * @return string */ - public function getSerial() { + public function getSerial() + { if (empty($this->serial)) { - $this->serial = md5(serialize($this->getAll())); + $this->serial = sha1(serialize($this->getAll())); } return $this->serial; } /** * Retrieves all directives, organized by namespace + * * @warning This is a pretty inefficient function, avoid if you can */ - public function getAll() { - if (!$this->finalized) $this->autoFinalize(); + public function getAll() + { + if (!$this->finalized) { + $this->autoFinalize(); + } $ret = array(); foreach ($this->plist->squash() as $name => $value) { list($ns, $key) = explode('.', $name, 2); @@ -230,10 +288,13 @@ class HTMLPurifier_Config /** * Sets a value to configuration. - * @param $key String key - * @param $value Mixed value + * + * @param string $key key + * @param mixed $value value + * @param mixed $a */ - public function set($key, $value, $a = null) { + public function set($key, $value, $a = null) + { if (strpos($key, '.') === false) { $namespace = $key; $directive = $value; @@ -243,18 +304,25 @@ class HTMLPurifier_Config } else { list($namespace) = explode('.', $key); } - if ($this->isFinalized('Cannot set directive after finalization')) return; + if ($this->isFinalized('Cannot set directive after finalization')) { + return; + } if (!isset($this->def->info[$key])) { - $this->triggerError('Cannot set undefined directive ' . htmlspecialchars($key) . ' to value', - E_USER_WARNING); + $this->triggerError( + 'Cannot set undefined directive ' . htmlspecialchars($key) . ' to value', + E_USER_WARNING + ); return; } $def = $this->def->info[$key]; if (isset($def->isAlias)) { if ($this->aliasMode) { - $this->triggerError('Double-aliases not allowed, please fix '. - 'ConfigSchema bug with' . $key, E_USER_ERROR); + $this->triggerError( + 'Double-aliases not allowed, please fix '. + 'ConfigSchema bug with' . $key, + E_USER_ERROR + ); return; } $this->aliasMode = true; @@ -278,7 +346,11 @@ class HTMLPurifier_Config try { $value = $this->parser->parse($value, $type, $allow_null); } catch (HTMLPurifier_VarParserException $e) { - $this->triggerError('Value for ' . $key . ' is of invalid type, should be ' . HTMLPurifier_VarParser::getTypeName($type), E_USER_WARNING); + $this->triggerError( + 'Value for ' . $key . ' is of invalid type, should be ' . + HTMLPurifier_VarParser::getTypeName($type), + E_USER_WARNING + ); return; } if (is_string($value) && is_object($def)) { @@ -288,8 +360,11 @@ class HTMLPurifier_Config } // check to see if the value is allowed if (isset($def->allowed) && !isset($def->allowed[$value])) { - $this->triggerError('Value not supported, valid values are: ' . - $this->_listify($def->allowed), E_USER_WARNING); + $this->triggerError( + 'Value not supported, valid values are: ' . + $this->_listify($def->allowed), + E_USER_WARNING + ); return; } } @@ -307,38 +382,102 @@ class HTMLPurifier_Config /** * Convenience function for error reporting + * + * @param array $lookup + * + * @return string */ - private function _listify($lookup) { + private function _listify($lookup) + { $list = array(); - foreach ($lookup as $name => $b) $list[] = $name; + foreach ($lookup as $name => $b) { + $list[] = $name; + } return implode(', ', $list); } /** * Retrieves object reference to the HTML definition. - * @param $raw Return a copy that has not been setup yet. Must be + * + * @param bool $raw Return a copy that has not been setup yet. Must be * called before it's been setup, otherwise won't work. - */ - public function getHTMLDefinition($raw = false) { - return $this->getDefinition('HTML', $raw); + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawHTMLDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_HTMLDefinition + */ + public function getHTMLDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('HTML', $raw, $optimized); } /** * Retrieves object reference to the CSS definition - * @param $raw Return a copy that has not been setup yet. Must be + * + * @param bool $raw Return a copy that has not been setup yet. Must be * called before it's been setup, otherwise won't work. - */ - public function getCSSDefinition($raw = false) { - return $this->getDefinition('CSS', $raw); + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawCSSDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_CSSDefinition + */ + public function getCSSDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('CSS', $raw, $optimized); + } + + /** + * Retrieves object reference to the URI definition + * + * @param bool $raw Return a copy that has not been setup yet. Must be + * called before it's been setup, otherwise won't work. + * @param bool $optimized If true, this method may return null, to + * indicate that a cached version of the modified + * definition object is available and no further edits + * are necessary. Consider using + * maybeGetRawURIDefinition, which is more explicitly + * named, instead. + * + * @return HTMLPurifier_URIDefinition + */ + public function getURIDefinition($raw = false, $optimized = false) + { + return $this->getDefinition('URI', $raw, $optimized); } /** * Retrieves a definition - * @param $type Type of definition: HTML, CSS, etc - * @param $raw Whether or not definition should be returned raw - */ - public function getDefinition($type, $raw = false) { - if (!$this->finalized) $this->autoFinalize(); + * + * @param string $type Type of definition: HTML, CSS, etc + * @param bool $raw Whether or not definition should be returned raw + * @param bool $optimized Only has an effect when $raw is true. Whether + * or not to return null if the result is already present in + * the cache. This is off by default for backwards + * compatibility reasons, but you need to do things this + * way in order to ensure that caching is done properly. + * Check out enduser-customize.html for more details. + * We probably won't ever change this default, as much as the + * maybe semantics is the "right thing to do." + * + * @throws HTMLPurifier_Exception + * @return HTMLPurifier_Definition + */ + public function getDefinition($type, $raw = false, $optimized = false) + { + if ($optimized && !$raw) { + throw new HTMLPurifier_Exception("Cannot set optimized = true when raw = false"); + } + if (!$this->finalized) { + $this->autoFinalize(); + } // temporarily suspend locks, so we can handle recursive definition calls $lock = $this->lock; $this->lock = null; @@ -346,61 +485,193 @@ class HTMLPurifier_Config $cache = $factory->create($type, $this); $this->lock = $lock; if (!$raw) { - // see if we can quickly supply a definition + // full definition + // --------------- + // check if definition is in memory + if (!empty($this->definitions[$type])) { + $def = $this->definitions[$type]; + // check if the definition is setup + if ($def->setup) { + return $def; + } else { + $def->setup($this); + if ($def->optimized) { + $cache->add($def, $this); + } + return $def; + } + } + // check if definition is in cache + $def = $cache->get($this); + if ($def) { + // definition in cache, save to memory and return it + $this->definitions[$type] = $def; + return $def; + } + // initialize it + $def = $this->initDefinition($type); + // set it up + $this->lock = $type; + $def->setup($this); + $this->lock = null; + // save in cache + $cache->add($def, $this); + // return it + return $def; + } else { + // raw definition + // -------------- + // check preconditions + $def = null; + if ($optimized) { + if (is_null($this->get($type . '.DefinitionID'))) { + // fatally error out if definition ID not set + throw new HTMLPurifier_Exception( + "Cannot retrieve raw version without specifying %$type.DefinitionID" + ); + } + } if (!empty($this->definitions[$type])) { - if (!$this->definitions[$type]->setup) { - $this->definitions[$type]->setup($this); - $cache->set($this->definitions[$type], $this); + $def = $this->definitions[$type]; + if ($def->setup && !$optimized) { + $extra = $this->chatty ? + " (try moving this code block earlier in your initialization)" : + ""; + throw new HTMLPurifier_Exception( + "Cannot retrieve raw definition after it has already been setup" . + $extra + ); + } + if ($def->optimized === null) { + $extra = $this->chatty ? " (try flushing your cache)" : ""; + throw new HTMLPurifier_Exception( + "Optimization status of definition is unknown" . $extra + ); + } + if ($def->optimized !== $optimized) { + $msg = $optimized ? "optimized" : "unoptimized"; + $extra = $this->chatty ? + " (this backtrace is for the first inconsistent call, which was for a $msg raw definition)" + : ""; + throw new HTMLPurifier_Exception( + "Inconsistent use of optimized and unoptimized raw definition retrievals" . $extra + ); } - return $this->definitions[$type]; } - // memory check missed, try cache - $this->definitions[$type] = $cache->get($this); - if ($this->definitions[$type]) { - // definition in cache, return it - return $this->definitions[$type]; + // check if definition was in memory + if ($def) { + if ($def->setup) { + // invariant: $optimized === true (checked above) + return null; + } else { + return $def; + } } - } elseif ( - !empty($this->definitions[$type]) && - !$this->definitions[$type]->setup - ) { - // raw requested, raw in memory, quick return - return $this->definitions[$type]; + // if optimized, check if definition was in cache + // (because we do the memory check first, this formulation + // is prone to cache slamming, but I think + // guaranteeing that either /all/ of the raw + // setup code or /none/ of it is run is more important.) + if ($optimized) { + // This code path only gets run once; once we put + // something in $definitions (which is guaranteed by the + // trailing code), we always short-circuit above. + $def = $cache->get($this); + if ($def) { + // save the full definition for later, but don't + // return it yet + $this->definitions[$type] = $def; + return null; + } + } + // check invariants for creation + if (!$optimized) { + if (!is_null($this->get($type . '.DefinitionID'))) { + if ($this->chatty) { + $this->triggerError( + 'Due to a documentation error in previous version of HTML Purifier, your ' . + 'definitions are not being cached. If this is OK, you can remove the ' . + '%$type.DefinitionRev and %$type.DefinitionID declaration. Otherwise, ' . + 'modify your code to use maybeGetRawDefinition, and test if the returned ' . + 'value is null before making any edits (if it is null, that means that a ' . + 'cached version is available, and no raw operations are necessary). See ' . + '<a href="http://htmlpurifier.org/docs/enduser-customize.html#optimized">' . + 'Customize</a> for more details', + E_USER_WARNING + ); + } else { + $this->triggerError( + "Useless DefinitionID declaration", + E_USER_WARNING + ); + } + } + } + // initialize it + $def = $this->initDefinition($type); + $def->optimized = $optimized; + return $def; } + throw new HTMLPurifier_Exception("The impossible happened!"); + } + + /** + * Initialise definition + * + * @param string $type What type of definition to create + * + * @return HTMLPurifier_CSSDefinition|HTMLPurifier_HTMLDefinition|HTMLPurifier_URIDefinition + * @throws HTMLPurifier_Exception + */ + private function initDefinition($type) + { // quick checks failed, let's create the object if ($type == 'HTML') { - $this->definitions[$type] = new HTMLPurifier_HTMLDefinition(); + $def = new HTMLPurifier_HTMLDefinition(); } elseif ($type == 'CSS') { - $this->definitions[$type] = new HTMLPurifier_CSSDefinition(); + $def = new HTMLPurifier_CSSDefinition(); } elseif ($type == 'URI') { - $this->definitions[$type] = new HTMLPurifier_URIDefinition(); + $def = new HTMLPurifier_URIDefinition(); } else { - throw new HTMLPurifier_Exception("Definition of $type type not supported"); + throw new HTMLPurifier_Exception( + "Definition of $type type not supported" + ); } - // quick abort if raw - if ($raw) { - if (is_null($this->get($type . '.DefinitionID'))) { - // fatally error out if definition ID not set - throw new HTMLPurifier_Exception("Cannot retrieve raw version without specifying %$type.DefinitionID"); - } - return $this->definitions[$type]; - } - // set it up - $this->lock = $type; - $this->definitions[$type]->setup($this); - $this->lock = null; - // save in cache - $cache->set($this->definitions[$type], $this); - return $this->definitions[$type]; + $this->definitions[$type] = $def; + return $def; + } + + public function maybeGetRawDefinition($name) + { + return $this->getDefinition($name, true, true); + } + + public function maybeGetRawHTMLDefinition() + { + return $this->getDefinition('HTML', true, true); + } + + public function maybeGetRawCSSDefinition() + { + return $this->getDefinition('CSS', true, true); + } + + public function maybeGetRawURIDefinition() + { + return $this->getDefinition('URI', true, true); } /** * Loads configuration values from an array with the following structure: * Namespace.Directive => Value - * @param $config_array Configuration associative array + * + * @param array $config_array Configuration associative array */ - public function loadArray($config_array) { - if ($this->isFinalized('Cannot load directives after finalization')) return; + public function loadArray($config_array) + { + if ($this->isFinalized('Cannot load directives after finalization')) { + return; + } foreach ($config_array as $key => $value) { $key = str_replace('_', '.', $key); if (strpos($key, '.') !== false) { @@ -408,8 +679,8 @@ class HTMLPurifier_Config } else { $namespace = $key; $namespace_values = $value; - foreach ($namespace_values as $directive => $value) { - $this->set($namespace .'.'. $directive, $value); + foreach ($namespace_values as $directive => $value2) { + $this->set($namespace .'.'. $directive, $value2); } } } @@ -419,40 +690,55 @@ class HTMLPurifier_Config * Returns a list of array(namespace, directive) for all directives * that are allowed in a web-form context as per an allowed * namespaces/directives list. - * @param $allowed List of allowed namespaces/directives - */ - public static function getAllowedDirectivesForForm($allowed, $schema = null) { + * + * @param array $allowed List of allowed namespaces/directives + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return array + */ + public static function getAllowedDirectivesForForm($allowed, $schema = null) + { if (!$schema) { $schema = HTMLPurifier_ConfigSchema::instance(); } if ($allowed !== true) { - if (is_string($allowed)) $allowed = array($allowed); - $allowed_ns = array(); - $allowed_directives = array(); - $blacklisted_directives = array(); - foreach ($allowed as $ns_or_directive) { - if (strpos($ns_or_directive, '.') !== false) { - // directive - if ($ns_or_directive[0] == '-') { - $blacklisted_directives[substr($ns_or_directive, 1)] = true; - } else { - $allowed_directives[$ns_or_directive] = true; - } - } else { - // namespace - $allowed_ns[$ns_or_directive] = true; - } - } + if (is_string($allowed)) { + $allowed = array($allowed); + } + $allowed_ns = array(); + $allowed_directives = array(); + $blacklisted_directives = array(); + foreach ($allowed as $ns_or_directive) { + if (strpos($ns_or_directive, '.') !== false) { + // directive + if ($ns_or_directive[0] == '-') { + $blacklisted_directives[substr($ns_or_directive, 1)] = true; + } else { + $allowed_directives[$ns_or_directive] = true; + } + } else { + // namespace + $allowed_ns[$ns_or_directive] = true; + } + } } $ret = array(); foreach ($schema->info as $key => $def) { list($ns, $directive) = explode('.', $key, 2); if ($allowed !== true) { - if (isset($blacklisted_directives["$ns.$directive"])) continue; - if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue; + if (isset($blacklisted_directives["$ns.$directive"])) { + continue; + } + if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) { + continue; + } + } + if (isset($def->isAlias)) { + continue; + } + if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') { + continue; } - if (isset($def->isAlias)) continue; - if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') continue; $ret[] = array($ns, $directive); } return $ret; @@ -461,13 +747,17 @@ class HTMLPurifier_Config /** * Loads configuration values from $_GET/$_POST that were posted * via ConfigForm - * @param $array $_GET or $_POST array to import - * @param $index Index/name that the config variables are in - * @param $allowed List of allowed namespaces/directives - * @param $mq_fix Boolean whether or not to enable magic quotes fix - * @param $schema Instance of HTMLPurifier_ConfigSchema to use, if not global copy - */ - public static function loadArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) { + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return mixed + */ + public static function loadArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) + { $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $schema); $config = HTMLPurifier_Config::create($ret, $schema); return $config; @@ -475,9 +765,14 @@ class HTMLPurifier_Config /** * Merges in configuration values from $_GET/$_POST to object. NOT STATIC. - * @note Same parameters as loadArrayFromForm - */ - public function mergeArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true) { + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + */ + public function mergeArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true) + { $ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $this->def); $this->loadArray($ret); } @@ -485,9 +780,20 @@ class HTMLPurifier_Config /** * Prepares an array from a form into something usable for the more * strict parts of HTMLPurifier_Config - */ - public static function prepareArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) { - if ($index !== false) $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array(); + * + * @param array $array $_GET or $_POST array to import + * @param string|bool $index Index/name that the config variables are in + * @param array|bool $allowed List of allowed namespaces/directives + * @param bool $mq_fix Boolean whether or not to enable magic quotes fix + * @param HTMLPurifier_ConfigSchema $schema Schema to use, if not global copy + * + * @return array + */ + public static function prepareArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) + { + if ($index !== false) { + $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array(); + } $mq = $mq_fix && function_exists('get_magic_quotes_gpc') && get_magic_quotes_gpc(); $allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $schema); @@ -499,7 +805,9 @@ class HTMLPurifier_Config $ret[$ns][$directive] = null; continue; } - if (!isset($array[$skey])) continue; + if (!isset($array[$skey])) { + continue; + } $value = $mq ? stripslashes($array[$skey]) : $array[$skey]; $ret[$ns][$directive] = $value; } @@ -508,19 +816,27 @@ class HTMLPurifier_Config /** * Loads configuration values from an ini file - * @param $filename Name of ini file + * + * @param string $filename Name of ini file */ - public function loadIni($filename) { - if ($this->isFinalized('Cannot load directives after finalization')) return; + public function loadIni($filename) + { + if ($this->isFinalized('Cannot load directives after finalization')) { + return; + } $array = parse_ini_file($filename, true); $this->loadArray($array); } /** * Checks whether or not the configuration object is finalized. - * @param $error String error message, or false for no error + * + * @param string|bool $error String error message, or false for no error + * + * @return bool */ - public function isFinalized($error = false) { + public function isFinalized($error = false) + { if ($this->finalized && $error) { $this->triggerError($error, E_USER_ERROR); } @@ -531,7 +847,8 @@ class HTMLPurifier_Config * Finalizes configuration only if auto finalize is on and not * already finalized */ - public function autoFinalize() { + public function autoFinalize() + { if ($this->autoFinalize) { $this->finalize(); } else { @@ -542,24 +859,35 @@ class HTMLPurifier_Config /** * Finalizes a configuration object, prohibiting further change */ - public function finalize() { + public function finalize() + { $this->finalized = true; - unset($this->parser); + $this->parser = null; } /** * Produces a nicely formatted error message by supplying the - * stack frame information from two levels up and OUTSIDE of - * HTMLPurifier_Config. + * stack frame information OUTSIDE of HTMLPurifier_Config. + * + * @param string $msg An error message + * @param int $no An error number */ - protected function triggerError($msg, $no) { + protected function triggerError($msg, $no) + { // determine previous stack frame - $backtrace = debug_backtrace(); - if ($this->chatty && isset($backtrace[1])) { - $frame = $backtrace[1]; - $extra = " on line {$frame['line']} in file {$frame['file']}"; - } else { - $extra = ''; + $extra = ''; + if ($this->chatty) { + $trace = debug_backtrace(); + // zip(tail(trace), trace) -- but PHP is not Haskell har har + for ($i = 0, $c = count($trace); $i < $c - 1; $i++) { + // XXX this is not correct on some versions of HTML Purifier + if ($trace[$i + 1]['class'] === 'HTMLPurifier_Config') { + continue; + } + $frame = $trace[$i]; + $extra = " invoked on line {$frame['line']} in file {$frame['file']}"; + break; + } } trigger_error($msg . $extra, $no); } @@ -567,8 +895,11 @@ class HTMLPurifier_Config /** * Returns a serialized form of the configuration object that can * be reconstituted. + * + * @return string */ - public function serialize() { + public function serialize() + { $this->getDefinition('HTML'); $this->getDefinition('CSS'); $this->getDefinition('URI'); diff --git a/library/HTMLPurifier/ConfigSchema.php b/library/HTMLPurifier/ConfigSchema.php index 67be5c71f..bfbb0f92f 100644 --- a/library/HTMLPurifier/ConfigSchema.php +++ b/library/HTMLPurifier/ConfigSchema.php @@ -3,21 +3,24 @@ /** * Configuration definition, defines directives and their defaults. */ -class HTMLPurifier_ConfigSchema { - +class HTMLPurifier_ConfigSchema +{ /** * Defaults of the directives and namespaces. + * @type array * @note This shares the exact same structure as HTMLPurifier_Config::$conf */ public $defaults = array(); /** * The default property list. Do not edit this property list. + * @type array */ public $defaultPlist; /** - * Definition of the directives. The structure of this is: + * Definition of the directives. + * The structure of this is: * * array( * 'Namespace' => array( @@ -44,29 +47,43 @@ class HTMLPurifier_ConfigSchema { * This class is friendly with HTMLPurifier_Config. If you need introspection * about the schema, you're better of using the ConfigSchema_Interchange, * which uses more memory but has much richer information. + * @type array */ public $info = array(); /** * Application-wide singleton + * @type HTMLPurifier_ConfigSchema */ - static protected $singleton; + protected static $singleton; - public function __construct() { + public function __construct() + { $this->defaultPlist = new HTMLPurifier_PropertyList(); } /** * Unserializes the default ConfigSchema. + * @return HTMLPurifier_ConfigSchema */ - public static function makeFromSerial() { - return unserialize(file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema.ser')); + public static function makeFromSerial() + { + $contents = file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema.ser'); + $r = unserialize($contents); + if (!$r) { + $hash = sha1($contents); + trigger_error("Unserialization of configuration schema failed, sha1 of file was $hash", E_USER_ERROR); + } + return $r; } /** * Retrieves an instance of the application-wide configuration definition. + * @param HTMLPurifier_ConfigSchema $prototype + * @return HTMLPurifier_ConfigSchema */ - public static function instance($prototype = null) { + public static function instance($prototype = null) + { if ($prototype !== null) { HTMLPurifier_ConfigSchema::$singleton = $prototype; } elseif (HTMLPurifier_ConfigSchema::$singleton === null || $prototype === true) { @@ -80,17 +97,19 @@ class HTMLPurifier_ConfigSchema { * @warning Will fail of directive's namespace is defined. * @warning This method's signature is slightly different from the legacy * define() static method! Beware! - * @param $namespace Namespace the directive is in - * @param $name Key of directive - * @param $default Default value of directive - * @param $type Allowed type of the directive. See + * @param string $key Name of directive + * @param mixed $default Default value of directive + * @param string $type Allowed type of the directive. See * HTMLPurifier_DirectiveDef::$type for allowed values - * @param $allow_null Whether or not to allow null values + * @param bool $allow_null Whether or not to allow null values */ - public function add($key, $default, $type, $allow_null) { + public function add($key, $default, $type, $allow_null) + { $obj = new stdclass(); $obj->type = is_int($type) ? $type : HTMLPurifier_VarParser::$types[$type]; - if ($allow_null) $obj->allow_null = true; + if ($allow_null) { + $obj->allow_null = true; + } $this->info[$key] = $obj; $this->defaults[$key] = $default; $this->defaultPlist->set($key, $default); @@ -101,11 +120,11 @@ class HTMLPurifier_ConfigSchema { * * Directive value aliases are convenient for developers because it lets * them set a directive to several values and get the same result. - * @param $namespace Directive's namespace - * @param $name Name of Directive - * @param $aliases Hash of aliased values to the real alias + * @param string $key Name of Directive + * @param array $aliases Hash of aliased values to the real alias */ - public function addValueAliases($key, $aliases) { + public function addValueAliases($key, $aliases) + { if (!isset($this->info[$key]->aliases)) { $this->info[$key]->aliases = array(); } @@ -118,22 +137,21 @@ class HTMLPurifier_ConfigSchema { * Defines a set of allowed values for a directive. * @warning This is slightly different from the corresponding static * method definition. - * @param $namespace Namespace of directive - * @param $name Name of directive - * @param $allowed Lookup array of allowed values + * @param string $key Name of directive + * @param array $allowed Lookup array of allowed values */ - public function addAllowedValues($key, $allowed) { + public function addAllowedValues($key, $allowed) + { $this->info[$key]->allowed = $allowed; } /** * Defines a directive alias for backwards compatibility - * @param $namespace - * @param $name Directive that will be aliased - * @param $new_namespace - * @param $new_name Directive that the alias will be to + * @param string $key Directive that will be aliased + * @param string $new_key Directive that the alias will be to */ - public function addAlias($key, $new_key) { + public function addAlias($key, $new_key) + { $obj = new stdclass; $obj->key = $new_key; $obj->isAlias = true; @@ -143,7 +161,8 @@ class HTMLPurifier_ConfigSchema { /** * Replaces any stdclass that only has the type property with type integer. */ - public function postProcess() { + public function postProcess() + { foreach ($this->info as $key => $v) { if (count((array) $v) == 1) { $this->info[$key] = $v->type; @@ -152,7 +171,6 @@ class HTMLPurifier_ConfigSchema { } } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php b/library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php index c05668a70..d5906cd46 100644 --- a/library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php +++ b/library/HTMLPurifier/ConfigSchema/Builder/ConfigSchema.php @@ -7,7 +7,12 @@ class HTMLPurifier_ConfigSchema_Builder_ConfigSchema { - public function build($interchange) { + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @return HTMLPurifier_ConfigSchema + */ + public function build($interchange) + { $schema = new HTMLPurifier_ConfigSchema(); foreach ($interchange->directives as $d) { $schema->add( @@ -38,7 +43,6 @@ class HTMLPurifier_ConfigSchema_Builder_ConfigSchema $schema->postProcess(); return $schema; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/Builder/Xml.php b/library/HTMLPurifier/ConfigSchema/Builder/Xml.php index 244561a37..5fa56f7dd 100644 --- a/library/HTMLPurifier/ConfigSchema/Builder/Xml.php +++ b/library/HTMLPurifier/ConfigSchema/Builder/Xml.php @@ -7,10 +7,21 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter { + /** + * @type HTMLPurifier_ConfigSchema_Interchange + */ protected $interchange; + + /** + * @type string + */ private $namespace; - protected function writeHTMLDiv($html) { + /** + * @param string $html + */ + protected function writeHTMLDiv($html) + { $this->startElement('div'); $purifier = HTMLPurifier::getInstance(); @@ -21,12 +32,23 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter $this->endElement(); // div } - protected function export($var) { - if ($var === array()) return 'array()'; + /** + * @param mixed $var + * @return string + */ + protected function export($var) + { + if ($var === array()) { + return 'array()'; + } return var_export($var, true); } - public function build($interchange) { + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + */ + public function build($interchange) + { // global access, only use as last resort $this->interchange = $interchange; @@ -39,19 +61,26 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter $this->buildDirective($directive); } - if ($this->namespace) $this->endElement(); // namespace + if ($this->namespace) { + $this->endElement(); + } // namespace $this->endElement(); // configdoc $this->flush(); } - public function buildDirective($directive) { - + /** + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive + */ + public function buildDirective($directive) + { // Kludge, although I suppose having a notion of a "root namespace" // certainly makes things look nicer when documentation is built. // Depends on things being sorted. if (!$this->namespace || $this->namespace !== $directive->id->getRootNamespace()) { - if ($this->namespace) $this->endElement(); // namespace + if ($this->namespace) { + $this->endElement(); + } // namespace $this->namespace = $directive->id->getRootNamespace(); $this->startElement('namespace'); $this->writeAttribute('id', $this->namespace); @@ -64,43 +93,52 @@ class HTMLPurifier_ConfigSchema_Builder_Xml extends XMLWriter $this->writeElement('name', $directive->id->getDirective()); $this->startElement('aliases'); - foreach ($directive->aliases as $alias) $this->writeElement('alias', $alias->toString()); + foreach ($directive->aliases as $alias) { + $this->writeElement('alias', $alias->toString()); + } $this->endElement(); // aliases $this->startElement('constraints'); - if ($directive->version) $this->writeElement('version', $directive->version); - $this->startElement('type'); - if ($directive->typeAllowsNull) $this->writeAttribute('allow-null', 'yes'); - $this->text($directive->type); - $this->endElement(); // type - if ($directive->allowed) { - $this->startElement('allowed'); - foreach ($directive->allowed as $value => $x) $this->writeElement('value', $value); - $this->endElement(); // allowed + if ($directive->version) { + $this->writeElement('version', $directive->version); + } + $this->startElement('type'); + if ($directive->typeAllowsNull) { + $this->writeAttribute('allow-null', 'yes'); + } + $this->text($directive->type); + $this->endElement(); // type + if ($directive->allowed) { + $this->startElement('allowed'); + foreach ($directive->allowed as $value => $x) { + $this->writeElement('value', $value); } - $this->writeElement('default', $this->export($directive->default)); - $this->writeAttribute('xml:space', 'preserve'); - if ($directive->external) { - $this->startElement('external'); - foreach ($directive->external as $project) $this->writeElement('project', $project); - $this->endElement(); + $this->endElement(); // allowed + } + $this->writeElement('default', $this->export($directive->default)); + $this->writeAttribute('xml:space', 'preserve'); + if ($directive->external) { + $this->startElement('external'); + foreach ($directive->external as $project) { + $this->writeElement('project', $project); } + $this->endElement(); + } $this->endElement(); // constraints if ($directive->deprecatedVersion) { $this->startElement('deprecated'); - $this->writeElement('version', $directive->deprecatedVersion); - $this->writeElement('use', $directive->deprecatedUse->toString()); + $this->writeElement('version', $directive->deprecatedVersion); + $this->writeElement('use', $directive->deprecatedUse->toString()); $this->endElement(); // deprecated } $this->startElement('description'); - $this->writeHTMLDiv($directive->description); + $this->writeHTMLDiv($directive->description); $this->endElement(); // description $this->endElement(); // directive } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/Interchange.php b/library/HTMLPurifier/ConfigSchema/Interchange.php index 91a5aa730..0e08ae8fe 100644 --- a/library/HTMLPurifier/ConfigSchema/Interchange.php +++ b/library/HTMLPurifier/ConfigSchema/Interchange.php @@ -10,18 +10,23 @@ class HTMLPurifier_ConfigSchema_Interchange /** * Name of the application this schema is describing. + * @type string */ public $name; /** * Array of Directive ID => array(directive info) + * @type HTMLPurifier_ConfigSchema_Interchange_Directive[] */ public $directives = array(); /** * Adds a directive array to $directives + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $directive + * @throws HTMLPurifier_ConfigSchema_Exception */ - public function addDirective($directive) { + public function addDirective($directive) + { if (isset($this->directives[$i = $directive->id->toString()])) { throw new HTMLPurifier_ConfigSchema_Exception("Cannot redefine directive '$i'"); } @@ -32,11 +37,11 @@ class HTMLPurifier_ConfigSchema_Interchange * Convenience function to perform standard validation. Throws exception * on failed validation. */ - public function validate() { + public function validate() + { $validator = new HTMLPurifier_ConfigSchema_Validator(); return $validator->validate($this); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/Interchange/Directive.php b/library/HTMLPurifier/ConfigSchema/Interchange/Directive.php index ac8be0d97..127a39a67 100644 --- a/library/HTMLPurifier/ConfigSchema/Interchange/Directive.php +++ b/library/HTMLPurifier/ConfigSchema/Interchange/Directive.php @@ -7,71 +7,83 @@ class HTMLPurifier_ConfigSchema_Interchange_Directive { /** - * ID of directive, instance of HTMLPurifier_ConfigSchema_Interchange_Id. + * ID of directive. + * @type HTMLPurifier_ConfigSchema_Interchange_Id */ public $id; /** - * String type, e.g. 'integer' or 'istring'. + * Type, e.g. 'integer' or 'istring'. + * @type string */ public $type; /** * Default value, e.g. 3 or 'DefaultVal'. + * @type mixed */ public $default; /** * HTML description. + * @type string */ public $description; /** - * Boolean whether or not null is allowed as a value. + * Whether or not null is allowed as a value. + * @type bool */ public $typeAllowsNull = false; /** - * Lookup table of allowed scalar values, e.g. array('allowed' => true). + * Lookup table of allowed scalar values. + * e.g. array('allowed' => true). * Null if all values are allowed. + * @type array */ public $allowed; /** - * List of aliases for the directive, + * List of aliases for the directive. * e.g. array(new HTMLPurifier_ConfigSchema_Interchange_Id('Ns', 'Dir'))). + * @type HTMLPurifier_ConfigSchema_Interchange_Id[] */ public $aliases = array(); /** * Hash of value aliases, e.g. array('alt' => 'real'). Null if value * aliasing is disabled (necessary for non-scalar types). + * @type array */ public $valueAliases; /** * Version of HTML Purifier the directive was introduced, e.g. '1.3.1'. * Null if the directive has always existed. + * @type string */ public $version; /** - * ID of directive that supercedes this old directive, is an instance - * of HTMLPurifier_ConfigSchema_Interchange_Id. Null if not deprecated. + * ID of directive that supercedes this old directive. + * Null if not deprecated. + * @type HTMLPurifier_ConfigSchema_Interchange_Id */ public $deprecatedUse; /** * Version of HTML Purifier this directive was deprecated. Null if not * deprecated. + * @type string */ public $deprecatedVersion; /** * List of external projects this directive depends on, e.g. array('CSSTidy'). + * @type array */ public $external = array(); - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/Interchange/Id.php b/library/HTMLPurifier/ConfigSchema/Interchange/Id.php index b9b3c6f5c..126f09d95 100644 --- a/library/HTMLPurifier/ConfigSchema/Interchange/Id.php +++ b/library/HTMLPurifier/ConfigSchema/Interchange/Id.php @@ -6,32 +6,53 @@ class HTMLPurifier_ConfigSchema_Interchange_Id { + /** + * @type string + */ public $key; - public function __construct($key) { + /** + * @param string $key + */ + public function __construct($key) + { $this->key = $key; } /** + * @return string * @warning This is NOT magic, to ensure that people don't abuse SPL and * cause problems for PHP 5.0 support. */ - public function toString() { + public function toString() + { return $this->key; } - public function getRootNamespace() { + /** + * @return string + */ + public function getRootNamespace() + { return substr($this->key, 0, strpos($this->key, ".")); } - public function getDirective() { + /** + * @return string + */ + public function getDirective() + { return substr($this->key, strpos($this->key, ".") + 1); } - public static function make($id) { + /** + * @param string $id + * @return HTMLPurifier_ConfigSchema_Interchange_Id + */ + public static function make($id) + { return new HTMLPurifier_ConfigSchema_Interchange_Id($id); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php b/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php index 785b72ce8..655e6dd1b 100644 --- a/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php +++ b/library/HTMLPurifier/ConfigSchema/InterchangeBuilder.php @@ -5,21 +5,39 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder /** * Used for processing DEFAULT, nothing else. + * @type HTMLPurifier_VarParser */ protected $varParser; - public function __construct($varParser = null) { + /** + * @param HTMLPurifier_VarParser $varParser + */ + public function __construct($varParser = null) + { $this->varParser = $varParser ? $varParser : new HTMLPurifier_VarParser_Native(); } - public static function buildFromDirectory($dir = null) { - $builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder(); + /** + * @param string $dir + * @return HTMLPurifier_ConfigSchema_Interchange + */ + public static function buildFromDirectory($dir = null) + { + $builder = new HTMLPurifier_ConfigSchema_InterchangeBuilder(); $interchange = new HTMLPurifier_ConfigSchema_Interchange(); return $builder->buildDir($interchange, $dir); } - public function buildDir($interchange, $dir = null) { - if (!$dir) $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema'; + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param string $dir + * @return HTMLPurifier_ConfigSchema_Interchange + */ + public function buildDir($interchange, $dir = null) + { + if (!$dir) { + $dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier/ConfigSchema/schema'; + } if (file_exists($dir . '/info.ini')) { $info = parse_ini_file($dir . '/info.ini'); $interchange->name = $info['name']; @@ -39,24 +57,30 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder foreach ($files as $file) { $this->buildFile($interchange, $dir . '/' . $file); } - return $interchange; } - public function buildFile($interchange, $file) { + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param string $file + */ + public function buildFile($interchange, $file) + { $parser = new HTMLPurifier_StringHashParser(); $this->build( $interchange, - new HTMLPurifier_StringHash( $parser->parseFile($file) ) + new HTMLPurifier_StringHash($parser->parseFile($file)) ); } /** * Builds an interchange object based on a hash. - * @param $interchange HTMLPurifier_ConfigSchema_Interchange object to build - * @param $hash HTMLPurifier_ConfigSchema_StringHash source data + * @param HTMLPurifier_ConfigSchema_Interchange $interchange HTMLPurifier_ConfigSchema_Interchange object to build + * @param HTMLPurifier_StringHash $hash source data + * @throws HTMLPurifier_ConfigSchema_Exception */ - public function build($interchange, $hash) { + public function build($interchange, $hash) + { if (!$hash instanceof HTMLPurifier_StringHash) { $hash = new HTMLPurifier_StringHash($hash); } @@ -75,7 +99,13 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder $this->_findUnused($hash); } - public function buildDirective($interchange, $hash) { + /** + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @param HTMLPurifier_StringHash $hash + * @throws HTMLPurifier_ConfigSchema_Exception + */ + public function buildDirective($interchange, $hash) + { $directive = new HTMLPurifier_ConfigSchema_Interchange_Directive(); // These are required elements: @@ -84,7 +114,9 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder if (isset($hash['TYPE'])) { $type = explode('/', $hash->offsetGet('TYPE')); - if (isset($type[1])) $directive->typeAllowsNull = true; + if (isset($type[1])) { + $directive->typeAllowsNull = true; + } $directive->type = $type[0]; } else { throw new HTMLPurifier_ConfigSchema_Exception("TYPE in directive hash '$id' not defined"); @@ -92,7 +124,11 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder if (isset($hash['DEFAULT'])) { try { - $directive->default = $this->varParser->parse($hash->offsetGet('DEFAULT'), $directive->type, $directive->typeAllowsNull); + $directive->default = $this->varParser->parse( + $hash->offsetGet('DEFAULT'), + $directive->type, + $directive->typeAllowsNull + ); } catch (HTMLPurifier_VarParserException $e) { throw new HTMLPurifier_ConfigSchema_Exception($e->getMessage() . " in DEFAULT in directive hash '$id'"); } @@ -139,34 +175,45 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder /** * Evaluates an array PHP code string without array() wrapper + * @param string $contents */ - protected function evalArray($contents) { - return eval('return array('. $contents .');'); + protected function evalArray($contents) + { + return eval('return array(' . $contents . ');'); } /** * Converts an array list into a lookup array. + * @param array $array + * @return array */ - protected function lookup($array) { + protected function lookup($array) + { $ret = array(); - foreach ($array as $val) $ret[$val] = true; + foreach ($array as $val) { + $ret[$val] = true; + } return $ret; } /** * Convenience function that creates an HTMLPurifier_ConfigSchema_Interchange_Id * object based on a string Id. + * @param string $id + * @return HTMLPurifier_ConfigSchema_Interchange_Id */ - protected function id($id) { + protected function id($id) + { return HTMLPurifier_ConfigSchema_Interchange_Id::make($id); } /** * Triggers errors for any unused keys passed in the hash; such keys * may indicate typos, missing values, etc. - * @param $hash Instance of ConfigSchema_StringHash to check. + * @param HTMLPurifier_StringHash $hash Hash to check. */ - protected function _findUnused($hash) { + protected function _findUnused($hash) + { $accessed = $hash->getAccessed(); foreach ($hash as $k => $v) { if (!isset($accessed[$k])) { @@ -174,7 +221,6 @@ class HTMLPurifier_ConfigSchema_InterchangeBuilder } } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/Validator.php b/library/HTMLPurifier/ConfigSchema/Validator.php index f374f6a02..fb3127788 100644 --- a/library/HTMLPurifier/ConfigSchema/Validator.php +++ b/library/HTMLPurifier/ConfigSchema/Validator.php @@ -12,36 +12,48 @@ class HTMLPurifier_ConfigSchema_Validator { /** - * Easy to access global objects. + * @type HTMLPurifier_ConfigSchema_Interchange */ - protected $interchange, $aliases; + protected $interchange; + + /** + * @type array + */ + protected $aliases; /** * Context-stack to provide easy to read error messages. + * @type array */ protected $context = array(); /** - * HTMLPurifier_VarParser to test default's type. + * to test default's type. + * @type HTMLPurifier_VarParser */ protected $parser; - public function __construct() { + public function __construct() + { $this->parser = new HTMLPurifier_VarParser(); } /** - * Validates a fully-formed interchange object. Throws an - * HTMLPurifier_ConfigSchema_Exception if there's a problem. + * Validates a fully-formed interchange object. + * @param HTMLPurifier_ConfigSchema_Interchange $interchange + * @return bool */ - public function validate($interchange) { + public function validate($interchange) + { $this->interchange = $interchange; $this->aliases = array(); // PHP is a bit lax with integer <=> string conversions in // arrays, so we don't use the identical !== comparison foreach ($interchange->directives as $i => $directive) { $id = $directive->id->toString(); - if ($i != $id) $this->error(false, "Integrity violation: key '$i' does not match internal id '$id'"); + if ($i != $id) { + $this->error(false, "Integrity violation: key '$i' does not match internal id '$id'"); + } $this->validateDirective($directive); } return true; @@ -49,8 +61,10 @@ class HTMLPurifier_ConfigSchema_Validator /** * Validates a HTMLPurifier_ConfigSchema_Interchange_Id object. + * @param HTMLPurifier_ConfigSchema_Interchange_Id $id */ - public function validateId($id) { + public function validateId($id) + { $id_string = $id->toString(); $this->context[] = "id '$id_string'"; if (!$id instanceof HTMLPurifier_ConfigSchema_Interchange_Id) { @@ -67,8 +81,10 @@ class HTMLPurifier_ConfigSchema_Validator /** * Validates a HTMLPurifier_ConfigSchema_Interchange_Directive object. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d */ - public function validateDirective($d) { + public function validateDirective($d) + { $id = $d->id->toString(); $this->context[] = "directive '$id'"; $this->validateId($d->id); @@ -108,9 +124,13 @@ class HTMLPurifier_ConfigSchema_Validator /** * Extra validation if $allowed member variable of * HTMLPurifier_ConfigSchema_Interchange_Directive is defined. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d */ - public function validateDirectiveAllowed($d) { - if (is_null($d->allowed)) return; + public function validateDirectiveAllowed($d) + { + if (is_null($d->allowed)) { + return; + } $this->with($d, 'allowed') ->assertNotEmpty() ->assertIsLookup(); // handled by InterchangeBuilder @@ -119,7 +139,9 @@ class HTMLPurifier_ConfigSchema_Validator } $this->context[] = 'allowed'; foreach ($d->allowed as $val => $x) { - if (!is_string($val)) $this->error("value $val", 'must be a string'); + if (!is_string($val)) { + $this->error("value $val", 'must be a string'); + } } array_pop($this->context); } @@ -127,15 +149,23 @@ class HTMLPurifier_ConfigSchema_Validator /** * Extra validation if $valueAliases member variable of * HTMLPurifier_ConfigSchema_Interchange_Directive is defined. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d */ - public function validateDirectiveValueAliases($d) { - if (is_null($d->valueAliases)) return; + public function validateDirectiveValueAliases($d) + { + if (is_null($d->valueAliases)) { + return; + } $this->with($d, 'valueAliases') ->assertIsArray(); // handled by InterchangeBuilder $this->context[] = 'valueAliases'; foreach ($d->valueAliases as $alias => $real) { - if (!is_string($alias)) $this->error("alias $alias", 'must be a string'); - if (!is_string($real)) $this->error("alias target $real from alias '$alias'", 'must be a string'); + if (!is_string($alias)) { + $this->error("alias $alias", 'must be a string'); + } + if (!is_string($real)) { + $this->error("alias target $real from alias '$alias'", 'must be a string'); + } if ($alias === $real) { $this->error("alias '$alias'", "must not be an alias to itself"); } @@ -155,8 +185,10 @@ class HTMLPurifier_ConfigSchema_Validator /** * Extra validation if $aliases member variable of * HTMLPurifier_ConfigSchema_Interchange_Directive is defined. + * @param HTMLPurifier_ConfigSchema_Interchange_Directive $d */ - public function validateDirectiveAliases($d) { + public function validateDirectiveAliases($d) + { $this->with($d, 'aliases') ->assertIsArray(); // handled by InterchangeBuilder $this->context[] = 'aliases'; @@ -180,27 +212,37 @@ class HTMLPurifier_ConfigSchema_Validator /** * Convenience function for generating HTMLPurifier_ConfigSchema_ValidatorAtom * for validating simple member variables of objects. + * @param $obj + * @param $member + * @return HTMLPurifier_ConfigSchema_ValidatorAtom */ - protected function with($obj, $member) { + protected function with($obj, $member) + { return new HTMLPurifier_ConfigSchema_ValidatorAtom($this->getFormattedContext(), $obj, $member); } /** * Emits an error, providing helpful context. + * @throws HTMLPurifier_ConfigSchema_Exception */ - protected function error($target, $msg) { - if ($target !== false) $prefix = ucfirst($target) . ' in ' . $this->getFormattedContext(); - else $prefix = ucfirst($this->getFormattedContext()); + protected function error($target, $msg) + { + if ($target !== false) { + $prefix = ucfirst($target) . ' in ' . $this->getFormattedContext(); + } else { + $prefix = ucfirst($this->getFormattedContext()); + } throw new HTMLPurifier_ConfigSchema_Exception(trim($prefix . ' ' . $msg)); } /** * Returns a formatted context string. + * @return string */ - protected function getFormattedContext() { + protected function getFormattedContext() + { return implode(' in ', array_reverse($this->context)); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/ValidatorAtom.php b/library/HTMLPurifier/ConfigSchema/ValidatorAtom.php index b95aea18c..c9aa3644a 100644 --- a/library/HTMLPurifier/ConfigSchema/ValidatorAtom.php +++ b/library/HTMLPurifier/ConfigSchema/ValidatorAtom.php @@ -8,59 +8,123 @@ */ class HTMLPurifier_ConfigSchema_ValidatorAtom { + /** + * @type string + */ + protected $context; - protected $context, $obj, $member, $contents; + /** + * @type object + */ + protected $obj; - public function __construct($context, $obj, $member) { - $this->context = $context; - $this->obj = $obj; - $this->member = $member; - $this->contents =& $obj->$member; + /** + * @type string + */ + protected $member; + + /** + * @type mixed + */ + protected $contents; + + public function __construct($context, $obj, $member) + { + $this->context = $context; + $this->obj = $obj; + $this->member = $member; + $this->contents =& $obj->$member; } - public function assertIsString() { - if (!is_string($this->contents)) $this->error('must be a string'); + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsString() + { + if (!is_string($this->contents)) { + $this->error('must be a string'); + } return $this; } - public function assertIsBool() { - if (!is_bool($this->contents)) $this->error('must be a boolean'); + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsBool() + { + if (!is_bool($this->contents)) { + $this->error('must be a boolean'); + } return $this; } - public function assertIsArray() { - if (!is_array($this->contents)) $this->error('must be an array'); + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsArray() + { + if (!is_array($this->contents)) { + $this->error('must be an array'); + } return $this; } - public function assertNotNull() { - if ($this->contents === null) $this->error('must not be null'); + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertNotNull() + { + if ($this->contents === null) { + $this->error('must not be null'); + } return $this; } - public function assertAlnum() { + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertAlnum() + { $this->assertIsString(); - if (!ctype_alnum($this->contents)) $this->error('must be alphanumeric'); + if (!ctype_alnum($this->contents)) { + $this->error('must be alphanumeric'); + } return $this; } - public function assertNotEmpty() { - if (empty($this->contents)) $this->error('must not be empty'); + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertNotEmpty() + { + if (empty($this->contents)) { + $this->error('must not be empty'); + } return $this; } - public function assertIsLookup() { + /** + * @return HTMLPurifier_ConfigSchema_ValidatorAtom + */ + public function assertIsLookup() + { $this->assertIsArray(); foreach ($this->contents as $v) { - if ($v !== true) $this->error('must be a lookup array'); + if ($v !== true) { + $this->error('must be a lookup array'); + } } return $this; } - protected function error($msg) { + /** + * @param string $msg + * @throws HTMLPurifier_ConfigSchema_Exception + */ + protected function error($msg) + { throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema.ser b/library/HTMLPurifier/ConfigSchema/schema.ser Binary files differindex 22b8d54a5..22ea32185 100644 --- a/library/HTMLPurifier/ConfigSchema/schema.ser +++ b/library/HTMLPurifier/ConfigSchema/schema.ser diff --git a/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt b/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt new file mode 100644 index 000000000..3fd465406 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/CSS.AllowedFonts.txt @@ -0,0 +1,12 @@ +CSS.AllowedFonts +TYPE: lookup/null +VERSION: 4.3.0 +DEFAULT: NULL +--DESCRIPTION-- +<p> + Allows you to manually specify a set of allowed fonts. If + <code>NULL</code>, all fonts are allowed. This directive + affects generic names (serif, sans-serif, monospace, cursive, + fantasy) as well as specific font families. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt b/library/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt new file mode 100644 index 000000000..f1f5c5f12 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/CSS.ForbiddenProperties.txt @@ -0,0 +1,13 @@ +CSS.ForbiddenProperties +TYPE: lookup +VERSION: 4.2.0 +DEFAULT: array() +--DESCRIPTION-- +<p> + This is the logical inverse of %CSS.AllowedProperties, and it will + override that directive or any other directive. If possible, + %CSS.AllowedProperties is recommended over this directive, + because it can sometimes be difficult to tell whether or not you've + forbidden all of the CSS properties you truly would like to disallow. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt b/library/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt new file mode 100644 index 000000000..e733a61e8 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/CSS.Trusted.txt @@ -0,0 +1,9 @@ +CSS.Trusted +TYPE: bool +VERSION: 4.2.1 +DEFAULT: false +--DESCRIPTION-- +Indicates whether or not the user's CSS input is trusted or not. If the +input is trusted, a more expansive set of allowed properties. See +also %HTML.Trusted. +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt b/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt new file mode 100644 index 000000000..b2b83d9ab --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPermissions.txt @@ -0,0 +1,11 @@ +Cache.SerializerPermissions +TYPE: int +VERSION: 4.3.0 +DEFAULT: 0755 +--DESCRIPTION-- + +<p> + Directory permissions of the files and directories created inside + the DefinitionCache/Serializer or other custom serializer path. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt new file mode 100644 index 000000000..2c910cc7d --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.AllowHostnameUnderscore.txt @@ -0,0 +1,16 @@ +Core.AllowHostnameUnderscore +TYPE: bool +VERSION: 4.6.0 +DEFAULT: false +--DESCRIPTION-- +<p> + By RFC 1123, underscores are not permitted in host names. + (This is in contrast to the specification for DNS, RFC + 2181, which allows underscores.) + However, most browsers do the right thing when faced with + an underscore in the host name, and so some poorly written + websites are written with the expectation this should work. + Setting this parameter to true relaxes our allowed character + check so that underscores are permitted. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt index 08b381d34..c572c14ec 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt @@ -24,5 +24,6 @@ array ( --DESCRIPTION-- Lookup array of color names to six digit hexadecimal number corresponding -to color, with preceding hash mark. Used when parsing colors. +to color, with preceding hash mark. Used when parsing colors. The lookup +is done in a case-insensitive manner. --# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt new file mode 100644 index 000000000..1cd4c2c96 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.DisableExcludes.txt @@ -0,0 +1,14 @@ +Core.DisableExcludes +TYPE: bool +DEFAULT: false +VERSION: 4.5.0 +--DESCRIPTION-- +<p> + This directive disables SGML-style exclusions, e.g. the exclusion of + <code><object></code> in any descendant of a + <code><pre></code> tag. Disabling excludes will allow some + invalid documents to pass through HTML Purifier, but HTML Purifier + will also be less likely to accidentally remove large documents during + processing. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt new file mode 100644 index 000000000..ce243c35d --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.EnableIDNA.txt @@ -0,0 +1,9 @@ +Core.EnableIDNA +TYPE: bool +DEFAULT: false +VERSION: 4.4.0 +--DESCRIPTION-- +Allows international domain names in URLs. This configuration option +requires the PEAR Net_IDNA2 module to be installed. It operates by +punycoding any internationalized host names for maximum portability. +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt index 4d5b5055c..a3881be75 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt @@ -2,9 +2,11 @@ Core.EscapeInvalidChildren TYPE: bool DEFAULT: false --DESCRIPTION-- -When true, a child is found that is not allowed in the context of the +<p><strong>Warning:</strong> this configuration option is no longer does anything as of 4.6.0.</p> + +<p>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. +child nodes.</p> --# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt new file mode 100644 index 000000000..d77f5360d --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.NormalizeNewlines.txt @@ -0,0 +1,11 @@ +Core.NormalizeNewlines +TYPE: bool +VERSION: 4.2.0 +DEFAULT: true +--DESCRIPTION-- +<p> + Whether or not to normalize newlines to the operating + system default. When <code>false</code>, HTML Purifier + will attempt to preserve mixed newline files. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt new file mode 100644 index 000000000..3397d9f71 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveProcessingInstructions.txt @@ -0,0 +1,11 @@ +Core.RemoveProcessingInstructions +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +Instead of escaping processing instructions in the form <code><? ... +?></code>, remove it out-right. This may be useful if the HTML +you are validating contains XML processing instruction gunk, however, +it can also be user-unfriendly for people attempting to post PHP +snippets. +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt b/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt index 7fa6536b2..321eaa2d8 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt @@ -4,6 +4,11 @@ VERSION: 3.1.0 DEFAULT: false --DESCRIPTION-- <p> + <strong>Warning:</strong> Deprecated in favor of %HTML.SafeObject and + %Output.FlashCompat (turn both on to allow YouTube videos and other + Flash content). +</p> +<p> This directive enables YouTube video embedding in HTML Purifier. Check <a href="http://htmlpurifier.org/docs/enduser-youtube.html">this document on embedding videos</a> for more information on what this filter does. diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt index 3e231d2d1..0b2c106da 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt @@ -5,11 +5,14 @@ DEFAULT: NULL --DESCRIPTION-- <p> - This is a convenience directive that rolls the functionality of - %HTML.AllowedElements and %HTML.AllowedAttributes into one directive. + This is a preferred convenience directive that combines + %HTML.AllowedElements and %HTML.AllowedAttributes. Specify elements and attributes that are allowed using: - <code>element1[attr1|attr2],element2...</code>. You can also use - newlines instead of commas to separate elements. + <code>element1[attr1|attr2],element2...</code>. For example, + if you would like to only allow paragraphs and links, specify + <code>a[href],p</code>. You can specify attributes that apply + to all elements using an asterisk, e.g. <code>*[lang]</code>. + You can also use newlines instead of commas to separate elements. </p> <p> <strong>Warning</strong>: diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt new file mode 100644 index 000000000..140e21423 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt @@ -0,0 +1,10 @@ +HTML.AllowedComments +TYPE: lookup +VERSION: 4.4.0 +DEFAULT: array() +--DESCRIPTION-- +A whitelist which indicates what explicit comment bodies should be +allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp +(these directives are union'ed together, so a comment is considered +valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt new file mode 100644 index 000000000..f22e977d4 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt @@ -0,0 +1,15 @@ +HTML.AllowedCommentsRegexp +TYPE: string/null +VERSION: 4.4.0 +DEFAULT: NULL +--DESCRIPTION-- +A regexp, which if it matches the body of a comment, indicates that +it should be allowed. Trailing and leading spaces are removed prior +to running this regular expression. +<strong>Warning:</strong> Make sure you specify +correct anchor metacharacters <code>^regex$</code>, otherwise you may accept +comments that you did not mean to! In particular, the regex <code>/foo|bar/</code> +is probably not sufficiently strict, since it also allows <code>foobar</code>. +See also %HTML.AllowedComments (these directives are union'ed together, +so a comment is considered valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt index 888d55819..1d3fa7907 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt @@ -4,12 +4,17 @@ VERSION: 1.3.0 DEFAULT: NULL --DESCRIPTION-- <p> - 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. + If HTML Purifier's tag set is unsatisfactory for your needs, you can + overload it with your own list of tags to allow. If you change + this, you probably also want to change %HTML.AllowedAttributes; see + also %HTML.Allowed which lets you set allowed elements and + attributes at the same time. +</p> +<p> + If you attempt to allow an element that HTML Purifier does not know + about, HTML Purifier will raise an error. You will need to manually + tell HTML Purifier about this element by using the + <a href="http://htmlpurifier.org/docs/enduser-customize.html">advanced customization features.</a> </p> <p> <strong>Warning:</strong> If another directive conflicts with the diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt new file mode 100644 index 000000000..7878dc0bf --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt @@ -0,0 +1,11 @@ +HTML.FlashAllowFullScreen +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +<p> + Whether or not to permit embedded Flash content from + %HTML.SafeObject to expand to the full screen. Corresponds to + the <code>allowFullScreen</code> parameter. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt new file mode 100644 index 000000000..700b30924 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt @@ -0,0 +1,7 @@ +HTML.Nofollow +TYPE: bool +VERSION: 4.3.0 +DEFAULT: FALSE +--DESCRIPTION-- +If enabled, nofollow rel attributes are added to all outgoing links. +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt new file mode 100644 index 000000000..5eb6ec2b5 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt @@ -0,0 +1,13 @@ +HTML.SafeIframe +TYPE: bool +VERSION: 4.4.0 +DEFAULT: false +--DESCRIPTION-- +<p> + Whether or not to permit iframe tags in untrusted documents. This + directive must be accompanied by a whitelist of permitted iframes, + such as %URI.SafeIframeRegexp, otherwise it will fatally error. + This directive has no effect on strict doctypes, as iframes are not + valid. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt new file mode 100644 index 000000000..5ebc7a19d --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt @@ -0,0 +1,10 @@ +HTML.SafeScripting +TYPE: lookup +VERSION: 4.5.0 +DEFAULT: array() +--DESCRIPTION-- +<p> + Whether or not to permit script tags to external scripts in documents. + Inline scripting is not allowed, and the script must match an explicit whitelist. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt new file mode 100644 index 000000000..587a16778 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt @@ -0,0 +1,8 @@ +HTML.TargetBlank +TYPE: bool +VERSION: 4.4.0 +DEFAULT: FALSE +--DESCRIPTION-- +If enabled, <code>target=blank</code> attributes are added to all outgoing links. +(This includes links from an HTTPS version of a page to an HTTP version.) +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt index 89133b1a3..1db9237e9 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt @@ -5,4 +5,5 @@ DEFAULT: false --DESCRIPTION-- Indicates whether or not the user input is trusted or not. If the input is trusted, a more expansive set of allowed tags and attributes will be used. +See also %CSS.Trusted. --# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt b/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt new file mode 100644 index 000000000..d6f0d9f29 --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt @@ -0,0 +1,15 @@ +Output.FixInnerHTML +TYPE: bool +VERSION: 4.3.0 +DEFAULT: true +--DESCRIPTION-- +<p> + If true, HTML Purifier will protect against Internet Explorer's + mishandling of the <code>innerHTML</code> attribute by appending + a space to any attribute that does not contain angled brackets, spaces + or quotes, but contains a backtick. This slightly changes the + semantics of any given attribute, so if this is unacceptable and + you do not use <code>innerHTML</code> on any of your pages, you can + turn this directive off. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt index ae3a913f2..666635a5f 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt @@ -12,6 +12,6 @@ array ( --DESCRIPTION-- Whitelist that defines the schemes that a URI is allowed to have. This prevents XSS attacks from using pseudo-schemes like javascript or mocha. -There is also support for the <code>data</code> URI scheme, but it is not -enabled by default. +There is also support for the <code>data</code> and <code>file</code> +URI schemes, but they are not enabled by default. --# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt index 51e6ea91f..f891de499 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt @@ -1,12 +1,15 @@ URI.DisableResources TYPE: bool -VERSION: 1.3.0 +VERSION: 4.2.0 DEFAULT: false --DESCRIPTION-- - <p> 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. </p> +<p> + <em>Note:</em> While this directive has been available since 1.3.0, + it didn't actually start doing anything until 4.2.0. +</p> --# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt index 0d00f62ea..1e17c1d46 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt @@ -11,7 +11,7 @@ DEFAULT: NULL to check if a URI has passed through HTML Purifier with this line: </p> -<pre>$checksum === sha1($secret_key . ':' . $url)</pre> +<pre>$checksum === hash_hmac("sha256", $url, $secret_key)</pre> <p> If the output is TRUE, the redirector script should accept the URI. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt new file mode 100644 index 000000000..79084832b --- /dev/null +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt @@ -0,0 +1,22 @@ +URI.SafeIframeRegexp +TYPE: string/null +VERSION: 4.4.0 +DEFAULT: NULL +--DESCRIPTION-- +<p> + A PCRE regular expression that will be matched against an iframe URI. This is + a relatively inflexible scheme, but works well enough for the most common + use-case of iframes: embedded video. This directive only has an effect if + %HTML.SafeIframe is enabled. Here are some example values: +</p> +<ul> + <li><code>%^http://www.youtube.com/embed/%</code> - Allow YouTube videos</li> + <li><code>%^http://player.vimeo.com/video/%</code> - Allow Vimeo videos</li> + <li><code>%^http://(www.youtube.com/embed/|player.vimeo.com/video/)%</code> - Allow both</li> +</ul> +<p> + Note that this directive does not give you enough granularity to, say, disable + all <code>autoplay</code> videos. Pipe up on the HTML Purifier forums if this + is a capability you want. +</p> +--# vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ContentSets.php b/library/HTMLPurifier/ContentSets.php index 3b6e96f5f..543e3f8f1 100644 --- a/library/HTMLPurifier/ContentSets.php +++ b/library/HTMLPurifier/ContentSets.php @@ -7,35 +7,42 @@ class HTMLPurifier_ContentSets { /** - * List of content set strings (pipe seperators) indexed by name. + * List of content set strings (pipe separators) indexed by name. + * @type array */ public $info = array(); /** * List of content set lookups (element => true) indexed by name. + * @type array * @note This is in HTMLPurifier_HTMLDefinition->info_content_sets */ public $lookup = array(); /** - * Synchronized list of defined content sets (keys of info) + * Synchronized list of defined content sets (keys of info). + * @type array */ protected $keys = array(); /** - * Synchronized list of defined content values (values of info) + * Synchronized list of defined content values (values of info). + * @type array */ protected $values = array(); /** * Merges in module's content sets, expands identifiers in the content * sets and populates the keys, values and lookup member variables. - * @param $modules List of HTMLPurifier_HTMLModule + * @param HTMLPurifier_HTMLModule[] $modules List of HTMLPurifier_HTMLModule */ - public function __construct($modules) { - if (!is_array($modules)) $modules = array($modules); + public function __construct($modules) + { + if (!is_array($modules)) { + $modules = array($modules); + } // populate content_sets based on module hints // sorry, no way of overloading - foreach ($modules as $module_i => $module) { + foreach ($modules as $module) { foreach ($module->content_sets as $key => $value) { $temp = $this->convertToLookup($value); if (isset($this->lookup[$key])) { @@ -70,11 +77,14 @@ class HTMLPurifier_ContentSets /** * Accepts a definition; generates and assigns a ChildDef for it - * @param $def HTMLPurifier_ElementDef reference - * @param $module Module that defined the ElementDef + * @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef reference + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef */ - public function generateChildDef(&$def, $module) { - if (!empty($def->child)) return; // already done! + public function generateChildDef(&$def, $module) + { + if (!empty($def->child)) { // already done! + return; + } $content_model = $def->content_model; if (is_string($content_model)) { // Assume that $this->keys is alphanumeric @@ -89,7 +99,8 @@ class HTMLPurifier_ContentSets $def->child = $this->getChildDef($def, $module); } - public function generateChildDefCallback($matches) { + public function generateChildDefCallback($matches) + { return $this->info[$matches[0]]; } @@ -98,10 +109,12 @@ class HTMLPurifier_ContentSets * member variables in HTMLPurifier_ElementDef * @note This will also defer to modules for custom HTMLPurifier_ChildDef * subclasses that need content set expansion - * @param $def HTMLPurifier_ElementDef to have ChildDef extracted + * @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef to have ChildDef extracted + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef * @return HTMLPurifier_ChildDef corresponding to ElementDef */ - public function getChildDef($def, $module) { + public function getChildDef($def, $module) + { $value = $def->content_model; if (is_object($value)) { trigger_error( @@ -126,7 +139,9 @@ class HTMLPurifier_ContentSets if ($module->defines_child_def) { // save a func call $return = $module->getChildDef($def); } - if ($return !== false) return $return; + if ($return !== false) { + return $return; + } // error-out trigger_error( 'Could not determine which ChildDef class to instantiate', @@ -138,18 +153,18 @@ class HTMLPurifier_ContentSets /** * Converts a string list of elements separated by pipes into * a lookup array. - * @param $string List of elements - * @return Lookup array of elements + * @param string $string List of elements + * @return array Lookup array of elements */ - protected function convertToLookup($string) { + protected function convertToLookup($string) + { $array = explode('|', str_replace(' ', '', $string)); $ret = array(); - foreach ($array as $i => $k) { + foreach ($array as $k) { $ret[$k] = true; } return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Context.php b/library/HTMLPurifier/Context.php index 9ddf0c547..00e509c85 100644 --- a/library/HTMLPurifier/Context.php +++ b/library/HTMLPurifier/Context.php @@ -12,18 +12,22 @@ class HTMLPurifier_Context /** * Private array that stores the references. + * @type array */ private $_storage = array(); /** * Registers a variable into the context. - * @param $name String name - * @param $ref Reference to variable to be registered + * @param string $name String name + * @param mixed $ref Reference to variable to be registered */ - public function register($name, &$ref) { - if (isset($this->_storage[$name])) { - trigger_error("Name $name produces collision, cannot re-register", - E_USER_ERROR); + public function register($name, &$ref) + { + if (array_key_exists($name, $this->_storage)) { + trigger_error( + "Name $name produces collision, cannot re-register", + E_USER_ERROR + ); return; } $this->_storage[$name] =& $ref; @@ -31,14 +35,18 @@ class HTMLPurifier_Context /** * Retrieves a variable reference from the context. - * @param $name String name - * @param $ignore_error Boolean whether or not to ignore error + * @param string $name String name + * @param bool $ignore_error Boolean whether or not to ignore error + * @return mixed */ - public function &get($name, $ignore_error = false) { - if (!isset($this->_storage[$name])) { + public function &get($name, $ignore_error = false) + { + if (!array_key_exists($name, $this->_storage)) { if (!$ignore_error) { - trigger_error("Attempted to retrieve non-existent variable $name", - E_USER_ERROR); + trigger_error( + "Attempted to retrieve non-existent variable $name", + E_USER_ERROR + ); } $var = null; // so we can return by reference return $var; @@ -47,13 +55,16 @@ class HTMLPurifier_Context } /** - * Destorys a variable in the context. - * @param $name String name + * Destroys a variable in the context. + * @param string $name String name */ - public function destroy($name) { - if (!isset($this->_storage[$name])) { - trigger_error("Attempted to destroy non-existent variable $name", - E_USER_ERROR); + public function destroy($name) + { + if (!array_key_exists($name, $this->_storage)) { + trigger_error( + "Attempted to destroy non-existent variable $name", + E_USER_ERROR + ); return; } unset($this->_storage[$name]); @@ -61,22 +72,24 @@ class HTMLPurifier_Context /** * Checks whether or not the variable exists. - * @param $name String name + * @param string $name String name + * @return bool */ - public function exists($name) { - return isset($this->_storage[$name]); + public function exists($name) + { + return array_key_exists($name, $this->_storage); } /** * Loads a series of variables from an associative array - * @param $context_array Assoc array of variables to load + * @param array $context_array Assoc array of variables to load */ - public function loadArray($context_array) { + public function loadArray($context_array) + { foreach ($context_array as $key => $discard) { $this->register($key, $context_array[$key]); } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Definition.php b/library/HTMLPurifier/Definition.php index a7408c974..bc6d43364 100644 --- a/library/HTMLPurifier/Definition.php +++ b/library/HTMLPurifier/Definition.php @@ -9,31 +9,47 @@ abstract class HTMLPurifier_Definition /** * Has setup() been called yet? + * @type bool */ public $setup = false; /** + * If true, write out the final definition object to the cache after + * setup. This will be true only if all invocations to get a raw + * definition object are also optimized. This does not cause file + * system thrashing because on subsequent calls the cached object + * is used and any writes to the raw definition object are short + * circuited. See enduser-customize.html for the high-level + * picture. + * @type bool + */ + public $optimized = null; + + /** * What type of definition is it? + * @type string */ public $type; /** * Sets up the definition object into the final form, something * not done by the constructor - * @param $config HTMLPurifier_Config instance + * @param HTMLPurifier_Config $config */ abstract protected function doSetup($config); /** * Setup function that aborts if already setup - * @param $config HTMLPurifier_Config instance + * @param HTMLPurifier_Config $config */ - public function setup($config) { - if ($this->setup) return; + public function setup($config) + { + if ($this->setup) { + return; + } $this->setup = true; $this->doSetup($config); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache.php b/library/HTMLPurifier/DefinitionCache.php index c6e1e388c..67bb5b1e6 100644 --- a/library/HTMLPurifier/DefinitionCache.php +++ b/library/HTMLPurifier/DefinitionCache.php @@ -10,22 +10,27 @@ */ abstract class HTMLPurifier_DefinitionCache { - + /** + * @type string + */ public $type; /** - * @param $name Type of definition objects this instance of the + * @param string $type Type of definition objects this instance of the * cache will handle. */ - public function __construct($type) { + public function __construct($type) + { $this->type = $type; } /** * Generates a unique identifier for a particular configuration - * @param Instance of HTMLPurifier_Config + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config + * @return string */ - public function generateKey($config) { + public function generateKey($config) + { return $config->version . ',' . // possibly replace with function calls $config->getBatchSerial($this->type) . ',' . $config->get($this->type . '.DefinitionRev'); @@ -34,30 +39,37 @@ abstract class HTMLPurifier_DefinitionCache /** * Tests whether or not a key is old with respect to the configuration's * version and revision number. - * @param $key Key to test - * @param $config Instance of HTMLPurifier_Config to test against + * @param string $key Key to test + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config to test against + * @return bool */ - public function isOld($key, $config) { - if (substr_count($key, ',') < 2) return true; + public function isOld($key, $config) + { + if (substr_count($key, ',') < 2) { + return true; + } list($version, $hash, $revision) = explode(',', $key, 3); $compare = version_compare($version, $config->version); // version mismatch, is always old - if ($compare != 0) return true; + if ($compare != 0) { + return true; + } // versions match, ids match, check revision number - if ( - $hash == $config->getBatchSerial($this->type) && - $revision < $config->get($this->type . '.DefinitionRev') - ) return true; + if ($hash == $config->getBatchSerial($this->type) && + $revision < $config->get($this->type . '.DefinitionRev')) { + return true; + } return false; } /** * Checks if a definition's type jives with the cache's type * @note Throws an error on failure - * @param $def Definition object to check - * @return Boolean true if good, false if not + * @param HTMLPurifier_Definition $def Definition object to check + * @return bool true if good, false if not */ - public function checkDefType($def) { + public function checkDefType($def) + { if ($def->type !== $this->type) { trigger_error("Cannot use definition of type {$def->type} in cache for {$this->type}"); return false; @@ -67,31 +79,40 @@ abstract class HTMLPurifier_DefinitionCache /** * Adds a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config */ abstract public function add($def, $config); /** * Unconditionally saves a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config */ abstract public function set($def, $config); /** * Replace an object in the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config */ abstract public function replace($def, $config); /** * Retrieves a definition object from the cache + * @param HTMLPurifier_Config $config */ abstract public function get($config); /** * Removes a definition object to the cache + * @param HTMLPurifier_Config $config */ abstract public function remove($config); /** * Clears all objects from cache + * @param HTMLPurifier_Config $config */ abstract public function flush($config); @@ -100,9 +121,9 @@ abstract class HTMLPurifier_DefinitionCache * @note Be carefuly implementing this method as flush. Flush must * not interfere with other Definition types, and cleanup() * should not be repeatedly called by userland code. + * @param HTMLPurifier_Config $config */ abstract public function cleanup($config); - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Decorator.php b/library/HTMLPurifier/DefinitionCache/Decorator.php index b0fb6d0cd..b57a51b6c 100644 --- a/library/HTMLPurifier/DefinitionCache/Decorator.php +++ b/library/HTMLPurifier/DefinitionCache/Decorator.php @@ -5,58 +5,108 @@ class HTMLPurifier_DefinitionCache_Decorator extends HTMLPurifier_DefinitionCach /** * Cache object we are decorating + * @type HTMLPurifier_DefinitionCache */ public $cache; - public function __construct() {} + /** + * The name of the decorator + * @var string + */ + public $name; + + public function __construct() + { + } /** * Lazy decorator function - * @param $cache Reference to cache object to decorate + * @param HTMLPurifier_DefinitionCache $cache Reference to cache object to decorate + * @return HTMLPurifier_DefinitionCache_Decorator */ - public function decorate(&$cache) { + public function decorate(&$cache) + { $decorator = $this->copy(); // reference is necessary for mocks in PHP 4 $decorator->cache =& $cache; - $decorator->type = $cache->type; + $decorator->type = $cache->type; return $decorator; } /** * Cross-compatible clone substitute + * @return HTMLPurifier_DefinitionCache_Decorator */ - public function copy() { + public function copy() + { return new HTMLPurifier_DefinitionCache_Decorator(); } - public function add($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { return $this->cache->add($def, $config); } - public function set($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { return $this->cache->set($def, $config); } - public function replace($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { return $this->cache->replace($def, $config); } - public function get($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { return $this->cache->get($config); } - public function remove($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function remove($config) + { return $this->cache->remove($config); } - public function flush($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function flush($config) + { return $this->cache->flush($config); } - public function cleanup($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function cleanup($config) + { return $this->cache->cleanup($config); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php b/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php index d4cc35c4b..4991777ce 100644 --- a/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php +++ b/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php @@ -4,40 +4,75 @@ * Definition cache decorator class that cleans up the cache * whenever there is a cache miss. */ -class HTMLPurifier_DefinitionCache_Decorator_Cleanup extends - HTMLPurifier_DefinitionCache_Decorator +class HTMLPurifier_DefinitionCache_Decorator_Cleanup extends HTMLPurifier_DefinitionCache_Decorator { - + /** + * @type string + */ public $name = 'Cleanup'; - public function copy() { + /** + * @return HTMLPurifier_DefinitionCache_Decorator_Cleanup + */ + public function copy() + { return new HTMLPurifier_DefinitionCache_Decorator_Cleanup(); } - public function add($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { $status = parent::add($def, $config); - if (!$status) parent::cleanup($config); + if (!$status) { + parent::cleanup($config); + } return $status; } - public function set($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { $status = parent::set($def, $config); - if (!$status) parent::cleanup($config); + if (!$status) { + parent::cleanup($config); + } return $status; } - public function replace($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { $status = parent::replace($def, $config); - if (!$status) parent::cleanup($config); + if (!$status) { + parent::cleanup($config); + } return $status; } - public function get($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { $ret = parent::get($config); - if (!$ret) parent::cleanup($config); + if (!$ret) { + parent::cleanup($config); + } return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Decorator/Memory.php b/library/HTMLPurifier/DefinitionCache/Decorator/Memory.php index 18f16d32b..d529dce48 100644 --- a/library/HTMLPurifier/DefinitionCache/Decorator/Memory.php +++ b/library/HTMLPurifier/DefinitionCache/Decorator/Memory.php @@ -5,42 +5,81 @@ * to PHP's memory; good for unit tests or circumstances where * there are lots of configuration objects floating around. */ -class HTMLPurifier_DefinitionCache_Decorator_Memory extends - HTMLPurifier_DefinitionCache_Decorator +class HTMLPurifier_DefinitionCache_Decorator_Memory extends HTMLPurifier_DefinitionCache_Decorator { - + /** + * @type array + */ protected $definitions; + + /** + * @type string + */ public $name = 'Memory'; - public function copy() { + /** + * @return HTMLPurifier_DefinitionCache_Decorator_Memory + */ + public function copy() + { return new HTMLPurifier_DefinitionCache_Decorator_Memory(); } - public function add($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { $status = parent::add($def, $config); - if ($status) $this->definitions[$this->generateKey($config)] = $def; + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } return $status; } - public function set($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { $status = parent::set($def, $config); - if ($status) $this->definitions[$this->generateKey($config)] = $def; + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } return $status; } - public function replace($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { $status = parent::replace($def, $config); - if ($status) $this->definitions[$this->generateKey($config)] = $def; + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } return $status; } - public function get($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { $key = $this->generateKey($config); - if (isset($this->definitions[$key])) return $this->definitions[$key]; + if (isset($this->definitions[$key])) { + return $this->definitions[$key]; + } $this->definitions[$key] = parent::get($config); return $this->definitions[$key]; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in b/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in index 21a8fcfda..b1fec8d36 100644 --- a/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in +++ b/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in @@ -5,43 +5,78 @@ require_once 'HTMLPurifier/DefinitionCache/Decorator.php'; /** * Definition cache decorator template. */ -class HTMLPurifier_DefinitionCache_Decorator_Template extends - HTMLPurifier_DefinitionCache_Decorator +class HTMLPurifier_DefinitionCache_Decorator_Template extends HTMLPurifier_DefinitionCache_Decorator { - var $name = 'Template'; // replace this + /** + * @type string + */ + public $name = 'Template'; // replace this - function copy() { + public function copy() + { // replace class name with yours return new HTMLPurifier_DefinitionCache_Decorator_Template(); } // remove methods you don't need - function add($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { return parent::add($def, $config); } - function set($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { return parent::set($def, $config); } - function replace($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { return parent::replace($def, $config); } - function get($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { return parent::get($config); } - function flush() { - return parent::flush(); + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function flush($config) + { + return parent::flush($config); } - function cleanup($config) { + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function cleanup($config) + { return parent::cleanup($config); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Null.php b/library/HTMLPurifier/DefinitionCache/Null.php index 41d97e734..d9a75ce22 100644 --- a/library/HTMLPurifier/DefinitionCache/Null.php +++ b/library/HTMLPurifier/DefinitionCache/Null.php @@ -6,34 +6,71 @@ class HTMLPurifier_DefinitionCache_Null extends HTMLPurifier_DefinitionCache { - public function add($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return bool + */ + public function add($def, $config) + { return false; } - public function set($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return bool + */ + public function set($def, $config) + { return false; } - public function replace($def, $config) { + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return bool + */ + public function replace($def, $config) + { return false; } - public function remove($config) { + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function remove($config) + { return false; } - public function get($config) { + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function get($config) + { return false; } - public function flush($config) { + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function flush($config) + { return false; } - public function cleanup($config) { + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function cleanup($config) + { return false; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Serializer.php b/library/HTMLPurifier/DefinitionCache/Serializer.php index 7a6aa93f0..ecacb88fe 100644 --- a/library/HTMLPurifier/DefinitionCache/Serializer.php +++ b/library/HTMLPurifier/DefinitionCache/Serializer.php @@ -1,83 +1,160 @@ <?php -class HTMLPurifier_DefinitionCache_Serializer extends - HTMLPurifier_DefinitionCache +class HTMLPurifier_DefinitionCache_Serializer extends HTMLPurifier_DefinitionCache { - public function add($def, $config) { - if (!$this->checkDefType($def)) return; + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function add($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } $file = $this->generateFilePath($config); - if (file_exists($file)) return false; - if (!$this->_prepareDir($config)) return false; - return $this->_write($file, serialize($def)); + if (file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); } - public function set($def, $config) { - if (!$this->checkDefType($def)) return; + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function set($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } $file = $this->generateFilePath($config); - if (!$this->_prepareDir($config)) return false; - return $this->_write($file, serialize($def)); + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); } - public function replace($def, $config) { - if (!$this->checkDefType($def)) return; + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function replace($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } $file = $this->generateFilePath($config); - if (!file_exists($file)) return false; - if (!$this->_prepareDir($config)) return false; - return $this->_write($file, serialize($def)); + if (!file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); } - public function get($config) { + /** + * @param HTMLPurifier_Config $config + * @return bool|HTMLPurifier_Config + */ + public function get($config) + { $file = $this->generateFilePath($config); - if (!file_exists($file)) return false; + if (!file_exists($file)) { + return false; + } return unserialize(file_get_contents($file)); } - public function remove($config) { + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function remove($config) + { $file = $this->generateFilePath($config); - if (!file_exists($file)) return false; + if (!file_exists($file)) { + return false; + } return unlink($file); } - public function flush($config) { - if (!$this->_prepareDir($config)) return false; + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function flush($config) + { + if (!$this->_prepareDir($config)) { + return false; + } $dir = $this->generateDirectoryPath($config); - $dh = opendir($dir); + $dh = opendir($dir); while (false !== ($filename = readdir($dh))) { - if (empty($filename)) continue; - if ($filename[0] === '.') continue; + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } unlink($dir . '/' . $filename); } } - public function cleanup($config) { - if (!$this->_prepareDir($config)) return false; + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function cleanup($config) + { + if (!$this->_prepareDir($config)) { + return false; + } $dir = $this->generateDirectoryPath($config); - $dh = opendir($dir); + $dh = opendir($dir); while (false !== ($filename = readdir($dh))) { - if (empty($filename)) continue; - if ($filename[0] === '.') continue; + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } $key = substr($filename, 0, strlen($filename) - 4); - if ($this->isOld($key, $config)) unlink($dir . '/' . $filename); + if ($this->isOld($key, $config)) { + unlink($dir . '/' . $filename); + } } } /** * Generates the file path to the serial file corresponding to * the configuration and definition name + * @param HTMLPurifier_Config $config + * @return string * @todo Make protected */ - public function generateFilePath($config) { + public function generateFilePath($config) + { $key = $this->generateKey($config); return $this->generateDirectoryPath($config) . '/' . $key . '.ser'; } /** * Generates the path to the directory contain this cache's serial files + * @param HTMLPurifier_Config $config + * @return string * @note No trailing slash * @todo Make protected */ - public function generateDirectoryPath($config) { + public function generateDirectoryPath($config) + { $base = $this->generateBaseDirectoryPath($config); return $base . '/' . $this->type; } @@ -85,9 +162,12 @@ class HTMLPurifier_DefinitionCache_Serializer extends /** * Generates path to base directory that contains all definition type * serials + * @param HTMLPurifier_Config $config + * @return mixed|string * @todo Make protected */ - public function generateBaseDirectoryPath($config) { + public function generateBaseDirectoryPath($config) + { $base = $config->get('Cache.SerializerPath'); $base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base; return $base; @@ -95,34 +175,54 @@ class HTMLPurifier_DefinitionCache_Serializer extends /** * Convenience wrapper function for file_put_contents - * @param $file File name to write to - * @param $data Data to write into file - * @return Number of bytes written if success, or false if failure. + * @param string $file File name to write to + * @param string $data Data to write into file + * @param HTMLPurifier_Config $config + * @return int|bool Number of bytes written if success, or false if failure. */ - private function _write($file, $data) { - return file_put_contents($file, $data); + private function _write($file, $data, $config) + { + $result = file_put_contents($file, $data); + if ($result !== false) { + // set permissions of the new file (no execute) + $chmod = $config->get('Cache.SerializerPermissions'); + if (!$chmod) { + $chmod = 0644; // invalid config or simpletest + } + $chmod = $chmod & 0666; + chmod($file, $chmod); + } + return $result; } /** * Prepares the directory that this type stores the serials in - * @return True if successful + * @param HTMLPurifier_Config $config + * @return bool True if successful */ - private function _prepareDir($config) { + private function _prepareDir($config) + { $directory = $this->generateDirectoryPath($config); + $chmod = $config->get('Cache.SerializerPermissions'); + if (!$chmod) { + $chmod = 0755; // invalid config or simpletest + } if (!is_dir($directory)) { $base = $this->generateBaseDirectoryPath($config); if (!is_dir($base)) { - trigger_error('Base directory '.$base.' does not exist, + trigger_error( + 'Base directory ' . $base . ' does not exist, please create or change using %Cache.SerializerPath', - E_USER_WARNING); + E_USER_WARNING + ); return false; - } elseif (!$this->_testPermissions($base)) { + } elseif (!$this->_testPermissions($base, $chmod)) { return false; } - $old = umask(0022); // disable group and world writes - mkdir($directory); + $old = umask(0000); + mkdir($directory, $chmod); umask($old); - } elseif (!$this->_testPermissions($directory)) { + } elseif (!$this->_testPermissions($directory, $chmod)) { return false; } return true; @@ -131,42 +231,55 @@ class HTMLPurifier_DefinitionCache_Serializer extends /** * Tests permissions on a directory and throws out friendly * error messages and attempts to chmod it itself if possible + * @param string $dir Directory path + * @param int $chmod Permissions + * @return bool True if directory is writable */ - private function _testPermissions($dir) { + private function _testPermissions($dir, $chmod) + { // early abort, if it is writable, everything is hunky-dory - if (is_writable($dir)) return true; + if (is_writable($dir)) { + return true; + } if (!is_dir($dir)) { // generally, you'll want to handle this beforehand // so a more specific error message can be given - trigger_error('Directory '.$dir.' does not exist', - E_USER_WARNING); + trigger_error( + 'Directory ' . $dir . ' does not exist', + E_USER_WARNING + ); return false; } if (function_exists('posix_getuid')) { // POSIX system, we can give more specific advice if (fileowner($dir) === posix_getuid()) { // we can chmod it ourselves - chmod($dir, 0755); - return true; + $chmod = $chmod | 0700; + if (chmod($dir, $chmod)) { + return true; + } } elseif (filegroup($dir) === posix_getgid()) { - $chmod = '775'; + $chmod = $chmod | 0070; } else { // PHP's probably running as nobody, so we'll // need to give global permissions - $chmod = '777'; + $chmod = $chmod | 0777; } - trigger_error('Directory '.$dir.' not writable, '. - 'please chmod to ' . $chmod, - E_USER_WARNING); + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please chmod to ' . decoct($chmod), + E_USER_WARNING + ); } else { // generic error message - trigger_error('Directory '.$dir.' not writable, '. + trigger_error( + 'Directory ' . $dir . ' not writable, ' . 'please alter file permissions', - E_USER_WARNING); + E_USER_WARNING + ); } return false; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/DefinitionCache/Serializer/README b/library/HTMLPurifier/DefinitionCache/Serializer/README index 2e35c1c3d..2e35c1c3d 100644..100755 --- a/library/HTMLPurifier/DefinitionCache/Serializer/README +++ b/library/HTMLPurifier/DefinitionCache/Serializer/README diff --git a/library/HTMLPurifier/DefinitionCacheFactory.php b/library/HTMLPurifier/DefinitionCacheFactory.php index a6ead6281..fd1cc9be4 100644 --- a/library/HTMLPurifier/DefinitionCacheFactory.php +++ b/library/HTMLPurifier/DefinitionCacheFactory.php @@ -5,22 +5,36 @@ */ class HTMLPurifier_DefinitionCacheFactory { - + /** + * @type array + */ protected $caches = array('Serializer' => array()); + + /** + * @type array + */ protected $implementations = array(); + + /** + * @type HTMLPurifier_DefinitionCache_Decorator[] + */ protected $decorators = array(); /** * Initialize default decorators */ - public function setup() { + public function setup() + { $this->addDecorator('Cleanup'); } /** * Retrieves an instance of global definition cache factory. + * @param HTMLPurifier_DefinitionCacheFactory $prototype + * @return HTMLPurifier_DefinitionCacheFactory */ - public static function instance($prototype = null) { + public static function instance($prototype = null) + { static $instance; if ($prototype !== null) { $instance = $prototype; @@ -33,19 +47,22 @@ class HTMLPurifier_DefinitionCacheFactory /** * Registers a new definition cache object - * @param $short Short name of cache object, for reference - * @param $long Full class name of cache object, for construction + * @param string $short Short name of cache object, for reference + * @param string $long Full class name of cache object, for construction */ - public function register($short, $long) { + public function register($short, $long) + { $this->implementations[$short] = $long; } /** * Factory method that creates a cache object based on configuration - * @param $name Name of definitions handled by cache - * @param $config Instance of HTMLPurifier_Config + * @param string $type Name of definitions handled by cache + * @param HTMLPurifier_Config $config Config instance + * @return mixed */ - public function create($type, $config) { + public function create($type, $config) + { $method = $config->get('Cache.DefinitionImpl'); if ($method === null) { return new HTMLPurifier_DefinitionCache_Null($type); @@ -53,10 +70,8 @@ class HTMLPurifier_DefinitionCacheFactory if (!empty($this->caches[$method][$type])) { return $this->caches[$method][$type]; } - if ( - isset($this->implementations[$method]) && - class_exists($class = $this->implementations[$method], false) - ) { + if (isset($this->implementations[$method]) && + class_exists($class = $this->implementations[$method], false)) { $cache = new $class($type); } else { if ($method != 'Serializer') { @@ -76,16 +91,16 @@ class HTMLPurifier_DefinitionCacheFactory /** * Registers a decorator to add to all new cache objects - * @param + * @param HTMLPurifier_DefinitionCache_Decorator|string $decorator An instance or the name of a decorator */ - public function addDecorator($decorator) { + public function addDecorator($decorator) + { if (is_string($decorator)) { $class = "HTMLPurifier_DefinitionCache_Decorator_$decorator"; $decorator = new $class; } $this->decorators[$decorator->name] = $decorator; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Doctype.php b/library/HTMLPurifier/Doctype.php index 1e3c574c0..4acd06e5b 100644 --- a/library/HTMLPurifier/Doctype.php +++ b/library/HTMLPurifier/Doctype.php @@ -10,42 +10,55 @@ class HTMLPurifier_Doctype { /** * Full name of doctype + * @type string */ public $name; /** * List of standard modules (string identifiers or literal objects) * that this doctype uses + * @type array */ public $modules = array(); /** * List of modules to use for tidying up code + * @type array */ public $tidyModules = array(); /** * Is the language derived from XML (i.e. XHTML)? + * @type bool */ public $xml = true; /** * List of aliases for this doctype + * @type array */ public $aliases = array(); /** * Public DTD identifier + * @type string */ public $dtdPublic; /** * System DTD identifier + * @type string */ public $dtdSystem; - public function __construct($name = null, $xml = true, $modules = array(), - $tidyModules = array(), $aliases = array(), $dtd_public = null, $dtd_system = null + public function __construct( + $name = null, + $xml = true, + $modules = array(), + $tidyModules = array(), + $aliases = array(), + $dtd_public = null, + $dtd_system = null ) { $this->name = $name; $this->xml = $xml; diff --git a/library/HTMLPurifier/DoctypeRegistry.php b/library/HTMLPurifier/DoctypeRegistry.php index 86049e939..acc1d64a6 100644 --- a/library/HTMLPurifier/DoctypeRegistry.php +++ b/library/HTMLPurifier/DoctypeRegistry.php @@ -4,12 +4,14 @@ class HTMLPurifier_DoctypeRegistry { /** - * Hash of doctype names to doctype objects + * Hash of doctype names to doctype objects. + * @type array */ protected $doctypes; /** - * Lookup table of aliases to real doctype names + * Lookup table of aliases to real doctype names. + * @type array */ protected $aliases; @@ -17,32 +19,57 @@ class HTMLPurifier_DoctypeRegistry * Registers a doctype to the registry * @note Accepts a fully-formed doctype object, or the * parameters for constructing a doctype object - * @param $doctype Name of doctype or literal doctype object - * @param $modules Modules doctype will load - * @param $modules_for_modes Modules doctype will load for certain modes - * @param $aliases Alias names for doctype - * @return Editable registered doctype + * @param string $doctype Name of doctype or literal doctype object + * @param bool $xml + * @param array $modules Modules doctype will load + * @param array $tidy_modules Modules doctype will load for certain modes + * @param array $aliases Alias names for doctype + * @param string $dtd_public + * @param string $dtd_system + * @return HTMLPurifier_Doctype Editable registered doctype */ - public function register($doctype, $xml = true, $modules = array(), - $tidy_modules = array(), $aliases = array(), $dtd_public = null, $dtd_system = null + public function register( + $doctype, + $xml = true, + $modules = array(), + $tidy_modules = array(), + $aliases = array(), + $dtd_public = null, + $dtd_system = null ) { - if (!is_array($modules)) $modules = array($modules); - if (!is_array($tidy_modules)) $tidy_modules = array($tidy_modules); - if (!is_array($aliases)) $aliases = array($aliases); + if (!is_array($modules)) { + $modules = array($modules); + } + if (!is_array($tidy_modules)) { + $tidy_modules = array($tidy_modules); + } + if (!is_array($aliases)) { + $aliases = array($aliases); + } if (!is_object($doctype)) { $doctype = new HTMLPurifier_Doctype( - $doctype, $xml, $modules, $tidy_modules, $aliases, $dtd_public, $dtd_system + $doctype, + $xml, + $modules, + $tidy_modules, + $aliases, + $dtd_public, + $dtd_system ); } $this->doctypes[$doctype->name] = $doctype; $name = $doctype->name; // hookup aliases foreach ($doctype->aliases as $alias) { - if (isset($this->doctypes[$alias])) continue; + if (isset($this->doctypes[$alias])) { + continue; + } $this->aliases[$alias] = $name; } // remove old aliases - if (isset($this->aliases[$name])) unset($this->aliases[$name]); + if (isset($this->aliases[$name])) { + unset($this->aliases[$name]); + } return $doctype; } @@ -50,11 +77,14 @@ class HTMLPurifier_DoctypeRegistry * Retrieves reference to a doctype of a certain name * @note This function resolves aliases * @note When possible, use the more fully-featured make() - * @param $doctype Name of doctype - * @return Editable doctype object + * @param string $doctype Name of doctype + * @return HTMLPurifier_Doctype Editable doctype object */ - public function get($doctype) { - if (isset($this->aliases[$doctype])) $doctype = $this->aliases[$doctype]; + public function get($doctype) + { + if (isset($this->aliases[$doctype])) { + $doctype = $this->aliases[$doctype]; + } if (!isset($this->doctypes[$doctype])) { trigger_error('Doctype ' . htmlspecialchars($doctype) . ' does not exist', E_USER_ERROR); $anon = new HTMLPurifier_Doctype($doctype); @@ -70,20 +100,30 @@ class HTMLPurifier_DoctypeRegistry * can hold on to (this is necessary in order to tell * Generator whether or not the current document is XML * based or not). + * @param HTMLPurifier_Config $config + * @return HTMLPurifier_Doctype */ - public function make($config) { + public function make($config) + { return clone $this->get($this->getDoctypeFromConfig($config)); } /** * Retrieves the doctype from the configuration object + * @param HTMLPurifier_Config $config + * @return string */ - public function getDoctypeFromConfig($config) { + public function getDoctypeFromConfig($config) + { // recommended test $doctype = $config->get('HTML.Doctype'); - if (!empty($doctype)) return $doctype; + if (!empty($doctype)) { + return $doctype; + } $doctype = $config->get('HTML.CustomDoctype'); - if (!empty($doctype)) return $doctype; + if (!empty($doctype)) { + return $doctype; + } // backwards-compatibility if ($config->get('HTML.XHTML')) { $doctype = 'XHTML 1.0'; @@ -97,7 +137,6 @@ class HTMLPurifier_DoctypeRegistry } return $doctype; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ElementDef.php b/library/HTMLPurifier/ElementDef.php index 5498d9567..d5311cedc 100644 --- a/library/HTMLPurifier/ElementDef.php +++ b/library/HTMLPurifier/ElementDef.php @@ -10,15 +10,16 @@ */ class HTMLPurifier_ElementDef { - /** * Does the definition work by itself, or is it created solely * for the purpose of merging into another definition? + * @type bool */ public $standalone = true; /** - * Associative array of attribute name to HTMLPurifier_AttrDef + * Associative array of attribute name to HTMLPurifier_AttrDef. + * @type array * @note Before being processed by HTMLPurifier_AttrCollections * when modules are finalized during * HTMLPurifier_HTMLDefinition->setup(), this array may also @@ -30,27 +31,43 @@ class HTMLPurifier_ElementDef */ public $attr = array(); + // XXX: Design note: currently, it's not possible to override + // previously defined AttrTransforms without messing around with + // the final generated config. This is by design; a previous version + // used an associated list of attr_transform, but it was extremely + // easy to accidentally override other attribute transforms by + // forgetting to specify an index (and just using 0.) While we + // could check this by checking the index number and complaining, + // there is a second problem which is that it is not at all easy to + // tell when something is getting overridden. Combine this with a + // codebase where this isn't really being used, and it's perfect for + // nuking. + /** - * Indexed list of tag's HTMLPurifier_AttrTransform to be done before validation + * List of tags HTMLPurifier_AttrTransform to be done before validation. + * @type array */ public $attr_transform_pre = array(); /** - * Indexed list of tag's HTMLPurifier_AttrTransform to be done after validation + * List of tags HTMLPurifier_AttrTransform to be done after validation. + * @type array */ public $attr_transform_post = array(); /** * HTMLPurifier_ChildDef of this tag. + * @type HTMLPurifier_ChildDef */ public $child; /** - * Abstract string representation of internal ChildDef rules. See - * HTMLPurifier_ContentSets for how this is parsed and then transformed + * Abstract string representation of internal ChildDef rules. + * @see HTMLPurifier_ContentSets for how this is parsed and then transformed * into an HTMLPurifier_ChildDef. * @warning This is a temporary variable that is not available after * being processed by HTMLDefinition + * @type string */ public $content_model; @@ -60,27 +77,29 @@ class HTMLPurifier_ElementDef * @warning This must be lowercase * @warning This is a temporary variable that is not available after * being processed by HTMLDefinition + * @type string */ public $content_model_type; - - /** * Does the element have a content model (#PCDATA | Inline)*? This * is important for chameleon ins and del processing in * HTMLPurifier_ChildDef_Chameleon. Dynamically set: modules don't * have to worry about this one. + * @type bool */ public $descendants_are_inline = false; /** - * List of the names of required attributes this element has. Dynamically - * populated by HTMLPurifier_HTMLDefinition::getElement + * List of the names of required attributes this element has. + * Dynamically populated by HTMLPurifier_HTMLDefinition::getElement() + * @type array */ public $required_attr = array(); /** * Lookup table of tags excluded from all descendants of this tag. + * @type array * @note SGML permits exclusions for all descendants, but this is * not possible with DTDs or XML Schemas. W3C has elected to * use complicated compositions of content_models to simulate @@ -94,6 +113,7 @@ class HTMLPurifier_ElementDef /** * This tag is explicitly auto-closed by the following tags. + * @type array */ public $autoclose = array(); @@ -101,19 +121,22 @@ class HTMLPurifier_ElementDef * If a foreign element is found in this element, test if it is * allowed by this sub-element; if it is, instead of closing the * current element, place it inside this element. + * @type string */ public $wrap; /** * Whether or not this is a formatting element affected by the * "Active Formatting Elements" algorithm. + * @type bool */ public $formatting; /** * Low-level factory constructor for creating new standalone element defs */ - public static function create($content_model, $content_model_type, $attr) { + public static function create($content_model, $content_model_type, $attr) + { $def = new HTMLPurifier_ElementDef(); $def->content_model = $content_model; $def->content_model_type = $content_model_type; @@ -125,11 +148,12 @@ class HTMLPurifier_ElementDef * Merges the values of another element definition into this one. * Values from the new element def take precedence if a value is * not mergeable. + * @param HTMLPurifier_ElementDef $def */ - public function mergeIn($def) { - + public function mergeIn($def) + { // later keys takes precedence - foreach($def->attr as $k => $v) { + foreach ($def->attr as $k => $v) { if ($k === 0) { // merge in the includes // sorry, no way to override an include @@ -139,28 +163,35 @@ class HTMLPurifier_ElementDef continue; } if ($v === false) { - if (isset($this->attr[$k])) unset($this->attr[$k]); + if (isset($this->attr[$k])) { + unset($this->attr[$k]); + } continue; } $this->attr[$k] = $v; } - $this->_mergeAssocArray($this->attr_transform_pre, $def->attr_transform_pre); - $this->_mergeAssocArray($this->attr_transform_post, $def->attr_transform_post); $this->_mergeAssocArray($this->excludes, $def->excludes); + $this->attr_transform_pre = array_merge($this->attr_transform_pre, $def->attr_transform_pre); + $this->attr_transform_post = array_merge($this->attr_transform_post, $def->attr_transform_post); - if(!empty($def->content_model)) { + if (!empty($def->content_model)) { $this->content_model = str_replace("#SUPER", $this->content_model, $def->content_model); $this->child = false; } - if(!empty($def->content_model_type)) { + if (!empty($def->content_model_type)) { $this->content_model_type = $def->content_model_type; $this->child = false; } - if(!is_null($def->child)) $this->child = $def->child; - if(!is_null($def->formatting)) $this->formatting = $def->formatting; - if($def->descendants_are_inline) $this->descendants_are_inline = $def->descendants_are_inline; - + if (!is_null($def->child)) { + $this->child = $def->child; + } + if (!is_null($def->formatting)) { + $this->formatting = $def->formatting; + } + if ($def->descendants_are_inline) { + $this->descendants_are_inline = $def->descendants_are_inline; + } } /** @@ -168,16 +199,18 @@ class HTMLPurifier_ElementDef * @param $a1 Array by reference that is merged into * @param $a2 Array that merges into $a1 */ - private function _mergeAssocArray(&$a1, $a2) { + private function _mergeAssocArray(&$a1, $a2) + { foreach ($a2 as $k => $v) { if ($v === false) { - if (isset($a1[$k])) unset($a1[$k]); + if (isset($a1[$k])) { + unset($a1[$k]); + } continue; } $a1[$k] = $v; } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Encoder.php b/library/HTMLPurifier/Encoder.php index 2b3140caa..fef9b5890 100644 --- a/library/HTMLPurifier/Encoder.php +++ b/library/HTMLPurifier/Encoder.php @@ -10,14 +10,90 @@ class HTMLPurifier_Encoder /** * Constructor throws fatal error if you attempt to instantiate class */ - private function __construct() { + private function __construct() + { trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR); } /** * Error-handler that mutes errors, alternative to shut-up operator. */ - public static function muteErrorHandler() {} + public static function muteErrorHandler() + { + } + + /** + * iconv wrapper which mutes errors, but doesn't work around bugs. + * @param string $in Input encoding + * @param string $out Output encoding + * @param string $text The text to convert + * @return string + */ + public static function unsafeIconv($in, $out, $text) + { + set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler')); + $r = iconv($in, $out, $text); + restore_error_handler(); + return $r; + } + + /** + * iconv wrapper which mutes errors and works around bugs. + * @param string $in Input encoding + * @param string $out Output encoding + * @param string $text The text to convert + * @param int $max_chunk_size + * @return string + */ + public static function iconv($in, $out, $text, $max_chunk_size = 8000) + { + $code = self::testIconvTruncateBug(); + if ($code == self::ICONV_OK) { + return self::unsafeIconv($in, $out, $text); + } elseif ($code == self::ICONV_TRUNCATES) { + // we can only work around this if the input character set + // is utf-8 + if ($in == 'utf-8') { + if ($max_chunk_size < 4) { + trigger_error('max_chunk_size is too small', E_USER_WARNING); + return false; + } + // split into 8000 byte chunks, but be careful to handle + // multibyte boundaries properly + if (($c = strlen($text)) <= $max_chunk_size) { + return self::unsafeIconv($in, $out, $text); + } + $r = ''; + $i = 0; + while (true) { + if ($i + $max_chunk_size >= $c) { + $r .= self::unsafeIconv($in, $out, substr($text, $i)); + break; + } + // wibble the boundary + if (0x80 != (0xC0 & ord($text[$i + $max_chunk_size]))) { + $chunk_size = $max_chunk_size; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 1]))) { + $chunk_size = $max_chunk_size - 1; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 2]))) { + $chunk_size = $max_chunk_size - 2; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 3]))) { + $chunk_size = $max_chunk_size - 3; + } else { + return false; // rather confusing UTF-8... + } + $chunk = substr($text, $i, $chunk_size); // substr doesn't mind overlong lengths + $r .= self::unsafeIconv($in, $out, $chunk); + $i += $chunk_size; + } + return $r; + } else { + return false; + } + } else { + return false; + } + } /** * Cleans a UTF-8 string for well-formedness and SGML validity @@ -25,6 +101,10 @@ class HTMLPurifier_Encoder * It will parse according to UTF-8 and return a valid UTF8 string, with * non-SGML codepoints excluded. * + * @param string $str The string to clean + * @param bool $force_php + * @return string + * * @note Just for reference, the non-SGML code points are 0 to 31 and * 127 to 159, inclusive. However, we allow code points 9, 10 * and 13, which are the tab, line feed and carriage return @@ -44,14 +124,17 @@ class HTMLPurifier_Encoder * would need that, and I'm probably not going to implement them. * Once again, PHP 6 should solve all our problems. */ - public static function cleanUTF8($str, $force_php = false) { - + public static function cleanUTF8($str, $force_php = false) + { // UTF-8 validity is checked since PHP 4.3.5 // This is an optimization: if the string is already valid UTF-8, no // need to do PHP stuff. 99% of the time, this will be the case. // The regexp matches the XML char production, as well as well as excluding // non-SGML codepoints U+007F to U+009F - if (preg_match('/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', $str)) { + if (preg_match( + '/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', + $str + )) { return $str; } @@ -70,7 +153,7 @@ class HTMLPurifier_Encoder $char = ''; $len = strlen($str); - for($i = 0; $i < $len; $i++) { + for ($i = 0; $i < $len; $i++) { $in = ord($str{$i}); $char .= $str[$i]; // append byte to char if (0 == $mState) { @@ -223,8 +306,9 @@ class HTMLPurifier_Encoder // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes // +----------+----------+----------+----------+ - public static function unichr($code) { - if($code > 1114111 or $code < 0 or + public static function unichr($code) + { + if ($code > 1114111 or $code < 0 or ($code >= 55296 and $code <= 57343) ) { // bits are set outside the "valid" range as defined // by UNICODE 4.1.0 @@ -242,7 +326,7 @@ class HTMLPurifier_Encoder $y = (($code & 2047) >> 6) | 192; } else { $y = (($code & 4032) >> 6) | 128; - if($code < 65536) { + if ($code < 65536) { $z = (($code >> 12) & 15) | 224; } else { $z = (($code >> 12) & 63) | 128; @@ -252,84 +336,129 @@ class HTMLPurifier_Encoder } // set up the actual character $ret = ''; - if($w) $ret .= chr($w); - if($z) $ret .= chr($z); - if($y) $ret .= chr($y); + if ($w) { + $ret .= chr($w); + } + if ($z) { + $ret .= chr($z); + } + if ($y) { + $ret .= chr($y); + } $ret .= chr($x); return $ret; } /** - * Converts a string to UTF-8 based on configuration. + * @return bool + */ + public static function iconvAvailable() + { + static $iconv = null; + if ($iconv === null) { + $iconv = function_exists('iconv') && self::testIconvTruncateBug() != self::ICONV_UNUSABLE; + } + return $iconv; + } + + /** + * Convert a string to UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string */ - public static function convertToUTF8($str, $config, $context) { + public static function convertToUTF8($str, $config, $context) + { $encoding = $config->get('Core.Encoding'); - if ($encoding === 'utf-8') return $str; + if ($encoding === 'utf-8') { + return $str; + } static $iconv = null; - if ($iconv === null) $iconv = function_exists('iconv'); - set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler')); + if ($iconv === null) { + $iconv = self::iconvAvailable(); + } if ($iconv && !$config->get('Test.ForceNoIconv')) { - $str = iconv($encoding, 'utf-8//IGNORE', $str); + // unaffected by bugs, since UTF-8 support all characters + $str = self::unsafeIconv($encoding, 'utf-8//IGNORE', $str); if ($str === false) { // $encoding is not a valid encoding - restore_error_handler(); trigger_error('Invalid encoding ' . $encoding, E_USER_ERROR); return ''; } // If the string is bjorked by Shift_JIS or a similar encoding // that doesn't support all of ASCII, convert the naughty // characters to their true byte-wise ASCII/UTF-8 equivalents. - $str = strtr($str, HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding)); - restore_error_handler(); + $str = strtr($str, self::testEncodingSupportsASCII($encoding)); return $str; } elseif ($encoding === 'iso-8859-1') { $str = utf8_encode($str); - restore_error_handler(); return $str; } - trigger_error('Encoding not supported, please install iconv', E_USER_ERROR); + $bug = HTMLPurifier_Encoder::testIconvTruncateBug(); + if ($bug == self::ICONV_OK) { + trigger_error('Encoding not supported, please install iconv', E_USER_ERROR); + } else { + trigger_error( + 'You have a buggy version of iconv, see https://bugs.php.net/bug.php?id=48147 ' . + 'and http://sourceware.org/bugzilla/show_bug.cgi?id=13541', + E_USER_ERROR + ); + } } /** * Converts a string from UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string * @note Currently, this is a lossy conversion, with unexpressable * characters being omitted. */ - public static function convertFromUTF8($str, $config, $context) { + public static function convertFromUTF8($str, $config, $context) + { $encoding = $config->get('Core.Encoding'); - if ($encoding === 'utf-8') return $str; - static $iconv = null; - if ($iconv === null) $iconv = function_exists('iconv'); if ($escape = $config->get('Core.EscapeNonASCIICharacters')) { - $str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str); + $str = self::convertToASCIIDumbLossless($str); + } + if ($encoding === 'utf-8') { + return $str; + } + static $iconv = null; + if ($iconv === null) { + $iconv = self::iconvAvailable(); } - set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler')); if ($iconv && !$config->get('Test.ForceNoIconv')) { // Undo our previous fix in convertToUTF8, otherwise iconv will barf - $ascii_fix = HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding); + $ascii_fix = self::testEncodingSupportsASCII($encoding); if (!$escape && !empty($ascii_fix)) { $clear_fix = array(); - foreach ($ascii_fix as $utf8 => $native) $clear_fix[$utf8] = ''; + foreach ($ascii_fix as $utf8 => $native) { + $clear_fix[$utf8] = ''; + } $str = strtr($str, $clear_fix); } $str = strtr($str, array_flip($ascii_fix)); // Normal stuff - $str = iconv('utf-8', $encoding . '//IGNORE', $str); - restore_error_handler(); + $str = self::iconv('utf-8', $encoding . '//IGNORE', $str); return $str; } elseif ($encoding === 'iso-8859-1') { $str = utf8_decode($str); - restore_error_handler(); return $str; } trigger_error('Encoding not supported', E_USER_ERROR); + // You might be tempted to assume that the ASCII representation + // might be OK, however, this is *not* universally true over all + // encodings. So we take the conservative route here, rather + // than forcibly turn on %Core.EscapeNonASCIICharacters } /** * Lossless (character-wise) conversion of HTML to ASCII - * @param $str UTF-8 string to be converted to ASCII - * @returns ASCII encoded string with non-ASCII character entity-ized + * @param string $str UTF-8 string to be converted to ASCII + * @return string ASCII encoded string with non-ASCII character entity-ized * @warning Adapted from MediaWiki, claiming fair use: this is a common * algorithm. If you disagree with this license fudgery, * implement it yourself. @@ -342,27 +471,28 @@ class HTMLPurifier_Encoder * @note Sort of with cleanUTF8() but it assumes that $str is * well-formed UTF-8 */ - public static function convertToASCIIDumbLossless($str) { + public static function convertToASCIIDumbLossless($str) + { $bytesleft = 0; $result = ''; $working = 0; $len = strlen($str); - for( $i = 0; $i < $len; $i++ ) { - $bytevalue = ord( $str[$i] ); - if( $bytevalue <= 0x7F ) { //0xxx xxxx - $result .= chr( $bytevalue ); + for ($i = 0; $i < $len; $i++) { + $bytevalue = ord($str[$i]); + if ($bytevalue <= 0x7F) { //0xxx xxxx + $result .= chr($bytevalue); $bytesleft = 0; - } elseif( $bytevalue <= 0xBF ) { //10xx xxxx + } elseif ($bytevalue <= 0xBF) { //10xx xxxx $working = $working << 6; $working += ($bytevalue & 0x3F); $bytesleft--; - if( $bytesleft <= 0 ) { + if ($bytesleft <= 0) { $result .= "&#" . $working . ";"; } - } elseif( $bytevalue <= 0xDF ) { //110x xxxx + } elseif ($bytevalue <= 0xDF) { //110x xxxx $working = $bytevalue & 0x1F; $bytesleft = 1; - } elseif( $bytevalue <= 0xEF ) { //1110 xxxx + } elseif ($bytevalue <= 0xEF) { //1110 xxxx $working = $bytevalue & 0x0F; $bytesleft = 2; } else { //1111 0xxx @@ -373,6 +503,54 @@ class HTMLPurifier_Encoder return $result; } + /** No bugs detected in iconv. */ + const ICONV_OK = 0; + + /** Iconv truncates output if converting from UTF-8 to another + * character set with //IGNORE, and a non-encodable character is found */ + const ICONV_TRUNCATES = 1; + + /** Iconv does not support //IGNORE, making it unusable for + * transcoding purposes */ + const ICONV_UNUSABLE = 2; + + /** + * glibc iconv has a known bug where it doesn't handle the magic + * //IGNORE stanza correctly. In particular, rather than ignore + * characters, it will return an EILSEQ after consuming some number + * of characters, and expect you to restart iconv as if it were + * an E2BIG. Old versions of PHP did not respect the errno, and + * returned the fragment, so as a result you would see iconv + * mysteriously truncating output. We can work around this by + * manually chopping our input into segments of about 8000 + * characters, as long as PHP ignores the error code. If PHP starts + * paying attention to the error code, iconv becomes unusable. + * + * @return int Error code indicating severity of bug. + */ + public static function testIconvTruncateBug() + { + static $code = null; + if ($code === null) { + // better not use iconv, otherwise infinite loop! + $r = self::unsafeIconv('utf-8', 'ascii//IGNORE', "\xCE\xB1" . str_repeat('a', 9000)); + if ($r === false) { + $code = self::ICONV_UNUSABLE; + } elseif (($c = strlen($r)) < 9000) { + $code = self::ICONV_TRUNCATES; + } elseif ($c > 9000) { + trigger_error( + 'Your copy of iconv is extremely buggy. Please notify HTML Purifier maintainers: ' . + 'include your iconv version as per phpversion()', + E_USER_ERROR + ); + } else { + $code = self::ICONV_OK; + } + } + return $code; + } + /** * This expensive function tests whether or not a given character * encoding supports ASCII. 7/8-bit encodings like Shift_JIS will @@ -384,10 +562,18 @@ class HTMLPurifier_Encoder * @return Array of UTF-8 characters to their corresponding ASCII, * which can be used to "undo" any overzealous iconv action. */ - public static function testEncodingSupportsASCII($encoding, $bypass = false) { + public static function testEncodingSupportsASCII($encoding, $bypass = false) + { + // All calls to iconv here are unsafe, proof by case analysis: + // If ICONV_OK, no difference. + // If ICONV_TRUNCATE, all calls involve one character inputs, + // so bug is not triggered. + // If ICONV_UNUSABLE, this call is irrelevant static $encodings = array(); if (!$bypass) { - if (isset($encodings[$encoding])) return $encodings[$encoding]; + if (isset($encodings[$encoding])) { + return $encodings[$encoding]; + } $lenc = strtolower($encoding); switch ($lenc) { case 'shift_jis': @@ -395,32 +581,31 @@ class HTMLPurifier_Encoder case 'johab': return array("\xE2\x82\xA9" => '\\'); } - if (strpos($lenc, 'iso-8859-') === 0) return array(); + if (strpos($lenc, 'iso-8859-') === 0) { + return array(); + } } $ret = array(); - set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler')); - if (iconv('UTF-8', $encoding, 'a') === false) return false; + if (self::unsafeIconv('UTF-8', $encoding, 'a') === false) { + return false; + } for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars $c = chr($i); // UTF-8 char - $r = iconv('UTF-8', "$encoding//IGNORE", $c); // initial conversion - if ( - $r === '' || + $r = self::unsafeIconv('UTF-8', "$encoding//IGNORE", $c); // initial conversion + if ($r === '' || // This line is needed for iconv implementations that do not // omit characters that do not exist in the target character set - ($r === $c && iconv($encoding, 'UTF-8//IGNORE', $r) !== $c) + ($r === $c && self::unsafeIconv($encoding, 'UTF-8//IGNORE', $r) !== $c) ) { // Reverse engineer: what's the UTF-8 equiv of this byte // sequence? This assumes that there's no variable width // encoding that doesn't support ASCII. - $ret[iconv($encoding, 'UTF-8//IGNORE', $c)] = $c; + $ret[self::unsafeIconv($encoding, 'UTF-8//IGNORE', $c)] = $c; } } - restore_error_handler(); $encodings[$encoding] = $ret; return $ret; } - - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/EntityLookup.php b/library/HTMLPurifier/EntityLookup.php index b4dfce94c..f12ff13a3 100644 --- a/library/HTMLPurifier/EntityLookup.php +++ b/library/HTMLPurifier/EntityLookup.php @@ -3,20 +3,23 @@ /** * Object that provides entity lookup table from entity name to character */ -class HTMLPurifier_EntityLookup { - +class HTMLPurifier_EntityLookup +{ /** * Assoc array of entity name to character represented. + * @type array */ public $table; /** * Sets up the entity lookup table from the serialized file contents. + * @param bool $file * @note The serialized contents are versioned, but were generated * using the maintenance script generate_entity_file.php * @warning This is not in constructor to help enforce the Singleton */ - public function setup($file = false) { + public function setup($file = false) + { if (!$file) { $file = HTMLPURIFIER_PREFIX . '/HTMLPurifier/EntityLookup/entities.ser'; } @@ -25,9 +28,11 @@ class HTMLPurifier_EntityLookup { /** * Retrieves sole instance of the object. - * @param Optional prototype of custom lookup table to overload with. + * @param bool|HTMLPurifier_EntityLookup $prototype Optional prototype of custom lookup table to overload with. + * @return HTMLPurifier_EntityLookup */ - public static function instance($prototype = false) { + public static function instance($prototype = false) + { // no references, since PHP doesn't copy unless modified static $instance = null; if ($prototype) { @@ -38,7 +43,6 @@ class HTMLPurifier_EntityLookup { } return $instance; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/EntityLookup/entities.ser b/library/HTMLPurifier/EntityLookup/entities.ser index f2b8b8f2d..e8b08128b 100644 --- a/library/HTMLPurifier/EntityLookup/entities.ser +++ b/library/HTMLPurifier/EntityLookup/entities.ser @@ -1 +1 @@ -a:246:{s:4:"nbsp";s:2:" ";s:5:"iexcl";s:2:"¡";s:4:"cent";s:2:"¢";s:5:"pound";s:2:"£";s:6:"curren";s:2:"¤";s:3:"yen";s:2:"¥";s:6:"brvbar";s:2:"¦";s:4:"sect";s:2:"§";s:3:"uml";s:2:"¨";s:4:"copy";s:2:"©";s:4:"ordf";s:2:"ª";s:5:"laquo";s:2:"«";s:3:"not";s:2:"¬";s:3:"shy";s:2:"";s:3:"reg";s:2:"®";s:4:"macr";s:2:"¯";s:3:"deg";s:2:"°";s:6:"plusmn";s:2:"±";s:5:"acute";s:2:"´";s:5:"micro";s:2:"µ";s:4:"para";s:2:"¶";s:6:"middot";s:2:"·";s:5:"cedil";s:2:"¸";s:4:"ordm";s:2:"º";s:5:"raquo";s:2:"»";s:6:"iquest";s:2:"¿";s:6:"Agrave";s:2:"À";s:6:"Aacute";s:2:"Á";s:5:"Acirc";s:2:"Â";s:6:"Atilde";s:2:"Ã";s:4:"Auml";s:2:"Ä";s:5:"Aring";s:2:"Å";s:5:"AElig";s:2:"Æ";s:6:"Ccedil";s:2:"Ç";s:6:"Egrave";s:2:"È";s:6:"Eacute";s:2:"É";s:5:"Ecirc";s:2:"Ê";s:4:"Euml";s:2:"Ë";s:6:"Igrave";s:2:"Ì";s:6:"Iacute";s:2:"Í";s:5:"Icirc";s:2:"Î";s:4:"Iuml";s:2:"Ï";s:3:"ETH";s:2:"Ð";s:6:"Ntilde";s:2:"Ñ";s:6:"Ograve";s:2:"Ò";s:6:"Oacute";s:2:"Ó";s:5:"Ocirc";s:2:"Ô";s:6:"Otilde";s:2:"Õ";s:4:"Ouml";s:2:"Ö";s:5:"times";s:2:"×";s:6:"Oslash";s:2:"Ø";s:6:"Ugrave";s:2:"Ù";s:6:"Uacute";s:2:"Ú";s:5:"Ucirc";s:2:"Û";s:4:"Uuml";s:2:"Ü";s:6:"Yacute";s:2:"Ý";s:5:"THORN";s:2:"Þ";s:5:"szlig";s:2:"ß";s:6:"agrave";s:2:"à";s:6:"aacute";s:2:"á";s:5:"acirc";s:2:"â";s:6:"atilde";s:2:"ã";s:4:"auml";s:2:"ä";s:5:"aring";s:2:"å";s:5:"aelig";s:2:"æ";s:6:"ccedil";s:2:"ç";s:6:"egrave";s:2:"è";s:6:"eacute";s:2:"é";s:5:"ecirc";s:2:"ê";s:4:"euml";s:2:"ë";s:6:"igrave";s:2:"ì";s:6:"iacute";s:2:"í";s:5:"icirc";s:2:"î";s:4:"iuml";s:2:"ï";s:3:"eth";s:2:"ð";s:6:"ntilde";s:2:"ñ";s:6:"ograve";s:2:"ò";s:6:"oacute";s:2:"ó";s:5:"ocirc";s:2:"ô";s:6:"otilde";s:2:"õ";s:4:"ouml";s:2:"ö";s:6:"divide";s:2:"÷";s:6:"oslash";s:2:"ø";s:6:"ugrave";s:2:"ù";s:6:"uacute";s:2:"ú";s:5:"ucirc";s:2:"û";s:4:"uuml";s:2:"ü";s:6:"yacute";s:2:"ý";s:5:"thorn";s:2:"þ";s:4:"yuml";s:2:"ÿ";s:4:"quot";s:1:""";s:3:"amp";s:1:"&";s:2:"lt";s:1:"<";s:2:"gt";s:1:">";s:4:"apos";s:1:"'";s:5:"OElig";s:2:"Œ";s:5:"oelig";s:2:"œ";s:6:"Scaron";s:2:"Š";s:6:"scaron";s:2:"š";s:4:"Yuml";s:2:"Ÿ";s:4:"circ";s:2:"ˆ";s:5:"tilde";s:2:"˜";s:4:"ensp";s:3:" ";s:4:"emsp";s:3:" ";s:6:"thinsp";s:3:" ";s:4:"zwnj";s:3:"";s:3:"zwj";s:3:"";s:3:"lrm";s:3:"";s:3:"rlm";s:3:"";s:5:"ndash";s:3:"–";s:5:"mdash";s:3:"—";s:5:"lsquo";s:3:"‘";s:5:"rsquo";s:3:"’";s:5:"sbquo";s:3:"‚";s:5:"ldquo";s:3:"“";s:5:"rdquo";s:3:"”";s:5:"bdquo";s:3:"„";s:6:"dagger";s:3:"†";s:6:"Dagger";s:3:"‡";s:6:"permil";s:3:"‰";s:6:"lsaquo";s:3:"‹";s:6:"rsaquo";s:3:"›";s:4:"euro";s:3:"€";s:4:"fnof";s:2:"ƒ";s:5:"Alpha";s:2:"Α";s:4:"Beta";s:2:"Β";s:5:"Gamma";s:2:"Γ";s:5:"Delta";s:2:"Δ";s:7:"Epsilon";s:2:"Ε";s:4:"Zeta";s:2:"Ζ";s:3:"Eta";s:2:"Η";s:5:"Theta";s:2:"Θ";s:4:"Iota";s:2:"Ι";s:5:"Kappa";s:2:"Κ";s:6:"Lambda";s:2:"Λ";s:2:"Mu";s:2:"Μ";s:2:"Nu";s:2:"Ν";s:2:"Xi";s:2:"Ξ";s:7:"Omicron";s:2:"Ο";s:2:"Pi";s:2:"Π";s:3:"Rho";s:2:"Ρ";s:5:"Sigma";s:2:"Σ";s:3:"Tau";s:2:"Τ";s:7:"Upsilon";s:2:"Υ";s:3:"Phi";s:2:"Φ";s:3:"Chi";s:2:"Χ";s:3:"Psi";s:2:"Ψ";s:5:"Omega";s:2:"Ω";s:5:"alpha";s:2:"α";s:4:"beta";s:2:"β";s:5:"gamma";s:2:"γ";s:5:"delta";s:2:"δ";s:7:"epsilon";s:2:"ε";s:4:"zeta";s:2:"ζ";s:3:"eta";s:2:"η";s:5:"theta";s:2:"θ";s:4:"iota";s:2:"ι";s:5:"kappa";s:2:"κ";s:6:"lambda";s:2:"λ";s:2:"mu";s:2:"μ";s:2:"nu";s:2:"ν";s:2:"xi";s:2:"ξ";s:7:"omicron";s:2:"ο";s:2:"pi";s:2:"π";s:3:"rho";s:2:"ρ";s:6:"sigmaf";s:2:"ς";s:5:"sigma";s:2:"σ";s:3:"tau";s:2:"τ";s:7:"upsilon";s:2:"υ";s:3:"phi";s:2:"φ";s:3:"chi";s:2:"χ";s:3:"psi";s:2:"ψ";s:5:"omega";s:2:"ω";s:8:"thetasym";s:2:"ϑ";s:5:"upsih";s:2:"ϒ";s:3:"piv";s:2:"ϖ";s:4:"bull";s:3:"•";s:6:"hellip";s:3:"…";s:5:"prime";s:3:"′";s:5:"Prime";s:3:"″";s:5:"oline";s:3:"‾";s:5:"frasl";s:3:"⁄";s:6:"weierp";s:3:"℘";s:5:"image";s:3:"ℑ";s:4:"real";s:3:"ℜ";s:5:"trade";s:3:"™";s:7:"alefsym";s:3:"ℵ";s:4:"larr";s:3:"←";s:4:"uarr";s:3:"↑";s:4:"rarr";s:3:"→";s:4:"darr";s:3:"↓";s:4:"harr";s:3:"↔";s:5:"crarr";s:3:"↵";s:4:"lArr";s:3:"⇐";s:4:"uArr";s:3:"⇑";s:4:"rArr";s:3:"⇒";s:4:"dArr";s:3:"⇓";s:4:"hArr";s:3:"⇔";s:6:"forall";s:3:"∀";s:4:"part";s:3:"∂";s:5:"exist";s:3:"∃";s:5:"empty";s:3:"∅";s:5:"nabla";s:3:"∇";s:4:"isin";s:3:"∈";s:5:"notin";s:3:"∉";s:2:"ni";s:3:"∋";s:4:"prod";s:3:"∏";s:3:"sum";s:3:"∑";s:5:"minus";s:3:"−";s:6:"lowast";s:3:"∗";s:5:"radic";s:3:"√";s:4:"prop";s:3:"∝";s:5:"infin";s:3:"∞";s:3:"ang";s:3:"∠";s:3:"and";s:3:"∧";s:2:"or";s:3:"∨";s:3:"cap";s:3:"∩";s:3:"cup";s:3:"∪";s:3:"int";s:3:"∫";s:3:"sim";s:3:"∼";s:4:"cong";s:3:"≅";s:5:"asymp";s:3:"≈";s:2:"ne";s:3:"≠";s:5:"equiv";s:3:"≡";s:2:"le";s:3:"≤";s:2:"ge";s:3:"≥";s:3:"sub";s:3:"⊂";s:3:"sup";s:3:"⊃";s:4:"nsub";s:3:"⊄";s:4:"sube";s:3:"⊆";s:4:"supe";s:3:"⊇";s:5:"oplus";s:3:"⊕";s:6:"otimes";s:3:"⊗";s:4:"perp";s:3:"⊥";s:4:"sdot";s:3:"⋅";s:5:"lceil";s:3:"⌈";s:5:"rceil";s:3:"⌉";s:6:"lfloor";s:3:"⌊";s:6:"rfloor";s:3:"⌋";s:4:"lang";s:3:"〈";s:4:"rang";s:3:"〉";s:3:"loz";s:3:"◊";s:6:"spades";s:3:"♠";s:5:"clubs";s:3:"♣";s:6:"hearts";s:3:"♥";s:5:"diams";s:3:"♦";}
\ No newline at end of file +a:253:{s:4:"fnof";s:2:"ƒ";s:5:"Alpha";s:2:"Α";s:4:"Beta";s:2:"Β";s:5:"Gamma";s:2:"Γ";s:5:"Delta";s:2:"Δ";s:7:"Epsilon";s:2:"Ε";s:4:"Zeta";s:2:"Ζ";s:3:"Eta";s:2:"Η";s:5:"Theta";s:2:"Θ";s:4:"Iota";s:2:"Ι";s:5:"Kappa";s:2:"Κ";s:6:"Lambda";s:2:"Λ";s:2:"Mu";s:2:"Μ";s:2:"Nu";s:2:"Ν";s:2:"Xi";s:2:"Ξ";s:7:"Omicron";s:2:"Ο";s:2:"Pi";s:2:"Π";s:3:"Rho";s:2:"Ρ";s:5:"Sigma";s:2:"Σ";s:3:"Tau";s:2:"Τ";s:7:"Upsilon";s:2:"Υ";s:3:"Phi";s:2:"Φ";s:3:"Chi";s:2:"Χ";s:3:"Psi";s:2:"Ψ";s:5:"Omega";s:2:"Ω";s:5:"alpha";s:2:"α";s:4:"beta";s:2:"β";s:5:"gamma";s:2:"γ";s:5:"delta";s:2:"δ";s:7:"epsilon";s:2:"ε";s:4:"zeta";s:2:"ζ";s:3:"eta";s:2:"η";s:5:"theta";s:2:"θ";s:4:"iota";s:2:"ι";s:5:"kappa";s:2:"κ";s:6:"lambda";s:2:"λ";s:2:"mu";s:2:"μ";s:2:"nu";s:2:"ν";s:2:"xi";s:2:"ξ";s:7:"omicron";s:2:"ο";s:2:"pi";s:2:"π";s:3:"rho";s:2:"ρ";s:6:"sigmaf";s:2:"ς";s:5:"sigma";s:2:"σ";s:3:"tau";s:2:"τ";s:7:"upsilon";s:2:"υ";s:3:"phi";s:2:"φ";s:3:"chi";s:2:"χ";s:3:"psi";s:2:"ψ";s:5:"omega";s:2:"ω";s:8:"thetasym";s:2:"ϑ";s:5:"upsih";s:2:"ϒ";s:3:"piv";s:2:"ϖ";s:4:"bull";s:3:"•";s:6:"hellip";s:3:"…";s:5:"prime";s:3:"′";s:5:"Prime";s:3:"″";s:5:"oline";s:3:"‾";s:5:"frasl";s:3:"⁄";s:6:"weierp";s:3:"℘";s:5:"image";s:3:"ℑ";s:4:"real";s:3:"ℜ";s:5:"trade";s:3:"™";s:7:"alefsym";s:3:"ℵ";s:4:"larr";s:3:"←";s:4:"uarr";s:3:"↑";s:4:"rarr";s:3:"→";s:4:"darr";s:3:"↓";s:4:"harr";s:3:"↔";s:5:"crarr";s:3:"↵";s:4:"lArr";s:3:"⇐";s:4:"uArr";s:3:"⇑";s:4:"rArr";s:3:"⇒";s:4:"dArr";s:3:"⇓";s:4:"hArr";s:3:"⇔";s:6:"forall";s:3:"∀";s:4:"part";s:3:"∂";s:5:"exist";s:3:"∃";s:5:"empty";s:3:"∅";s:5:"nabla";s:3:"∇";s:4:"isin";s:3:"∈";s:5:"notin";s:3:"∉";s:2:"ni";s:3:"∋";s:4:"prod";s:3:"∏";s:3:"sum";s:3:"∑";s:5:"minus";s:3:"−";s:6:"lowast";s:3:"∗";s:5:"radic";s:3:"√";s:4:"prop";s:3:"∝";s:5:"infin";s:3:"∞";s:3:"ang";s:3:"∠";s:3:"and";s:3:"∧";s:2:"or";s:3:"∨";s:3:"cap";s:3:"∩";s:3:"cup";s:3:"∪";s:3:"int";s:3:"∫";s:6:"there4";s:3:"∴";s:3:"sim";s:3:"∼";s:4:"cong";s:3:"≅";s:5:"asymp";s:3:"≈";s:2:"ne";s:3:"≠";s:5:"equiv";s:3:"≡";s:2:"le";s:3:"≤";s:2:"ge";s:3:"≥";s:3:"sub";s:3:"⊂";s:3:"sup";s:3:"⊃";s:4:"nsub";s:3:"⊄";s:4:"sube";s:3:"⊆";s:4:"supe";s:3:"⊇";s:5:"oplus";s:3:"⊕";s:6:"otimes";s:3:"⊗";s:4:"perp";s:3:"⊥";s:4:"sdot";s:3:"⋅";s:5:"lceil";s:3:"⌈";s:5:"rceil";s:3:"⌉";s:6:"lfloor";s:3:"⌊";s:6:"rfloor";s:3:"⌋";s:4:"lang";s:3:"〈";s:4:"rang";s:3:"〉";s:3:"loz";s:3:"◊";s:6:"spades";s:3:"♠";s:5:"clubs";s:3:"♣";s:6:"hearts";s:3:"♥";s:5:"diams";s:3:"♦";s:4:"quot";s:1:""";s:3:"amp";s:1:"&";s:2:"lt";s:1:"<";s:2:"gt";s:1:">";s:4:"apos";s:1:"'";s:5:"OElig";s:2:"Œ";s:5:"oelig";s:2:"œ";s:6:"Scaron";s:2:"Š";s:6:"scaron";s:2:"š";s:4:"Yuml";s:2:"Ÿ";s:4:"circ";s:2:"ˆ";s:5:"tilde";s:2:"˜";s:4:"ensp";s:3:" ";s:4:"emsp";s:3:" ";s:6:"thinsp";s:3:" ";s:4:"zwnj";s:3:"";s:3:"zwj";s:3:"";s:3:"lrm";s:3:"";s:3:"rlm";s:3:"";s:5:"ndash";s:3:"–";s:5:"mdash";s:3:"—";s:5:"lsquo";s:3:"‘";s:5:"rsquo";s:3:"’";s:5:"sbquo";s:3:"‚";s:5:"ldquo";s:3:"“";s:5:"rdquo";s:3:"”";s:5:"bdquo";s:3:"„";s:6:"dagger";s:3:"†";s:6:"Dagger";s:3:"‡";s:6:"permil";s:3:"‰";s:6:"lsaquo";s:3:"‹";s:6:"rsaquo";s:3:"›";s:4:"euro";s:3:"€";s:4:"nbsp";s:2:" ";s:5:"iexcl";s:2:"¡";s:4:"cent";s:2:"¢";s:5:"pound";s:2:"£";s:6:"curren";s:2:"¤";s:3:"yen";s:2:"¥";s:6:"brvbar";s:2:"¦";s:4:"sect";s:2:"§";s:3:"uml";s:2:"¨";s:4:"copy";s:2:"©";s:4:"ordf";s:2:"ª";s:5:"laquo";s:2:"«";s:3:"not";s:2:"¬";s:3:"shy";s:2:"";s:3:"reg";s:2:"®";s:4:"macr";s:2:"¯";s:3:"deg";s:2:"°";s:6:"plusmn";s:2:"±";s:4:"sup2";s:2:"²";s:4:"sup3";s:2:"³";s:5:"acute";s:2:"´";s:5:"micro";s:2:"µ";s:4:"para";s:2:"¶";s:6:"middot";s:2:"·";s:5:"cedil";s:2:"¸";s:4:"sup1";s:2:"¹";s:4:"ordm";s:2:"º";s:5:"raquo";s:2:"»";s:6:"frac14";s:2:"¼";s:6:"frac12";s:2:"½";s:6:"frac34";s:2:"¾";s:6:"iquest";s:2:"¿";s:6:"Agrave";s:2:"À";s:6:"Aacute";s:2:"Á";s:5:"Acirc";s:2:"Â";s:6:"Atilde";s:2:"Ã";s:4:"Auml";s:2:"Ä";s:5:"Aring";s:2:"Å";s:5:"AElig";s:2:"Æ";s:6:"Ccedil";s:2:"Ç";s:6:"Egrave";s:2:"È";s:6:"Eacute";s:2:"É";s:5:"Ecirc";s:2:"Ê";s:4:"Euml";s:2:"Ë";s:6:"Igrave";s:2:"Ì";s:6:"Iacute";s:2:"Í";s:5:"Icirc";s:2:"Î";s:4:"Iuml";s:2:"Ï";s:3:"ETH";s:2:"Ð";s:6:"Ntilde";s:2:"Ñ";s:6:"Ograve";s:2:"Ò";s:6:"Oacute";s:2:"Ó";s:5:"Ocirc";s:2:"Ô";s:6:"Otilde";s:2:"Õ";s:4:"Ouml";s:2:"Ö";s:5:"times";s:2:"×";s:6:"Oslash";s:2:"Ø";s:6:"Ugrave";s:2:"Ù";s:6:"Uacute";s:2:"Ú";s:5:"Ucirc";s:2:"Û";s:4:"Uuml";s:2:"Ü";s:6:"Yacute";s:2:"Ý";s:5:"THORN";s:2:"Þ";s:5:"szlig";s:2:"ß";s:6:"agrave";s:2:"à";s:6:"aacute";s:2:"á";s:5:"acirc";s:2:"â";s:6:"atilde";s:2:"ã";s:4:"auml";s:2:"ä";s:5:"aring";s:2:"å";s:5:"aelig";s:2:"æ";s:6:"ccedil";s:2:"ç";s:6:"egrave";s:2:"è";s:6:"eacute";s:2:"é";s:5:"ecirc";s:2:"ê";s:4:"euml";s:2:"ë";s:6:"igrave";s:2:"ì";s:6:"iacute";s:2:"í";s:5:"icirc";s:2:"î";s:4:"iuml";s:2:"ï";s:3:"eth";s:2:"ð";s:6:"ntilde";s:2:"ñ";s:6:"ograve";s:2:"ò";s:6:"oacute";s:2:"ó";s:5:"ocirc";s:2:"ô";s:6:"otilde";s:2:"õ";s:4:"ouml";s:2:"ö";s:6:"divide";s:2:"÷";s:6:"oslash";s:2:"ø";s:6:"ugrave";s:2:"ù";s:6:"uacute";s:2:"ú";s:5:"ucirc";s:2:"û";s:4:"uuml";s:2:"ü";s:6:"yacute";s:2:"ý";s:5:"thorn";s:2:"þ";s:4:"yuml";s:2:"ÿ";}
\ No newline at end of file diff --git a/library/HTMLPurifier/EntityParser.php b/library/HTMLPurifier/EntityParser.php index 8c384472d..61529dcd9 100644 --- a/library/HTMLPurifier/EntityParser.php +++ b/library/HTMLPurifier/EntityParser.php @@ -12,19 +12,21 @@ class HTMLPurifier_EntityParser /** * Reference to entity lookup table. + * @type HTMLPurifier_EntityLookup */ protected $_entity_lookup; /** * Callback regex string for parsing entities. + * @type string */ protected $_substituteEntitiesRegex = -'/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/'; -// 1. hex 2. dec 3. string (XML style) - + '/&(?:[#]x([a-fA-F0-9]+)|[#]0*(\d+)|([A-Za-z_:][A-Za-z0-9.\-_:]*));?/'; + // 1. hex 2. dec 3. string (XML style) /** * Decimal to parsed string conversion table for special entities. + * @type array */ protected $_special_dec2str = array( @@ -37,6 +39,7 @@ class HTMLPurifier_EntityParser /** * Stripped entity names to decimal conversion table for special entities. + * @type array */ protected $_special_ent2dec = array( @@ -51,41 +54,45 @@ class HTMLPurifier_EntityParser * running this whenever you have parsed character is t3h 5uck, we run * it before everything else. * - * @param $string String to have non-special entities parsed. - * @returns Parsed string. + * @param string $string String to have non-special entities parsed. + * @return string Parsed string. */ - public function substituteNonSpecialEntities($string) { + public function substituteNonSpecialEntities($string) + { // it will try to detect missing semicolons, but don't rely on it return preg_replace_callback( $this->_substituteEntitiesRegex, array($this, 'nonSpecialEntityCallback'), $string - ); + ); } /** * Callback function for substituteNonSpecialEntities() that does the work. * - * @param $matches PCRE matches array, with 0 the entire match, and + * @param array $matches PCRE matches array, with 0 the entire match, and * either index 1, 2 or 3 set with a hex value, dec value, * or string (respectively). - * @returns Replacement string. + * @return string Replacement string. */ - protected function nonSpecialEntityCallback($matches) { + protected function nonSpecialEntityCallback($matches) + { // replaces all but big five $entity = $matches[0]; $is_num = (@$matches[0][1] === '#'); if ($is_num) { $is_hex = (@$entity[2] === 'x'); $code = $is_hex ? hexdec($matches[1]) : (int) $matches[2]; - // abort for special characters - if (isset($this->_special_dec2str[$code])) return $entity; - + if (isset($this->_special_dec2str[$code])) { + return $entity; + } return HTMLPurifier_Encoder::unichr($code); } else { - if (isset($this->_special_ent2dec[$matches[3]])) return $entity; + if (isset($this->_special_ent2dec[$matches[3]])) { + return $entity; + } if (!$this->_entity_lookup) { $this->_entity_lookup = HTMLPurifier_EntityLookup::instance(); } @@ -103,14 +110,16 @@ class HTMLPurifier_EntityParser * @notice We try to avoid calling this function because otherwise, it * would have to be called a lot (for every parsed section). * - * @param $string String to have non-special entities parsed. - * @returns Parsed string. + * @param string $string String to have non-special entities parsed. + * @return string Parsed string. */ - public function substituteSpecialEntities($string) { + public function substituteSpecialEntities($string) + { return preg_replace_callback( $this->_substituteEntitiesRegex, array($this, 'specialEntityCallback'), - $string); + $string + ); } /** @@ -118,12 +127,13 @@ class HTMLPurifier_EntityParser * * This callback has same syntax as nonSpecialEntityCallback(). * - * @param $matches PCRE-style matches array, with 0 the entire match, and + * @param array $matches PCRE-style matches array, with 0 the entire match, and * either index 1, 2 or 3 set with a hex value, dec value, * or string (respectively). - * @returns Replacement string. + * @return string Replacement string. */ - protected function specialEntityCallback($matches) { + protected function specialEntityCallback($matches) + { $entity = $matches[0]; $is_num = (@$matches[0][1] === '#'); if ($is_num) { @@ -138,7 +148,6 @@ class HTMLPurifier_EntityParser $entity; } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ErrorCollector.php b/library/HTMLPurifier/ErrorCollector.php index 6713eaf77..d47e3f2e2 100644 --- a/library/HTMLPurifier/ErrorCollector.php +++ b/library/HTMLPurifier/ErrorCollector.php @@ -16,16 +16,46 @@ class HTMLPurifier_ErrorCollector const MESSAGE = 2; const CHILDREN = 3; + /** + * @type array + */ protected $errors; + + /** + * @type array + */ protected $_current; + + /** + * @type array + */ protected $_stacks = array(array()); + + /** + * @type HTMLPurifier_Language + */ protected $locale; + + /** + * @type HTMLPurifier_Generator + */ protected $generator; + + /** + * @type HTMLPurifier_Context + */ protected $context; + /** + * @type array + */ protected $lines = array(); - public function __construct($context) { + /** + * @param HTMLPurifier_Context $context + */ + public function __construct($context) + { $this->locale =& $context->get('Locale'); $this->context = $context; $this->_current =& $this->_stacks[0]; @@ -34,13 +64,11 @@ class HTMLPurifier_ErrorCollector /** * Sends an error message to the collector for later use - * @param $severity int Error severity, PHP error style (don't use E_USER_) - * @param $msg string Error message text - * @param $subst1 string First substitution for $msg - * @param $subst2 string ... + * @param int $severity Error severity, PHP error style (don't use E_USER_) + * @param string $msg Error message text */ - public function send($severity, $msg) { - + public function send($severity, $msg) + { $args = array(); if (func_num_args() > 2) { $args = func_get_args(); @@ -50,7 +78,7 @@ class HTMLPurifier_ErrorCollector $token = $this->context->get('CurrentToken', true); $line = $token ? $token->line : $this->context->get('CurrentLine', true); - $col = $token ? $token->col : $this->context->get('CurrentCol', true); + $col = $token ? $token->col : $this->context->get('CurrentCol', true); $attr = $this->context->get('CurrentAttr', true); // perform special substitutions, also add custom parameters @@ -60,7 +88,9 @@ class HTMLPurifier_ErrorCollector } if (!is_null($attr)) { $subst['$CurrentAttr.Name'] = $attr; - if (isset($token->attr[$attr])) $subst['$CurrentAttr.Value'] = $token->attr[$attr]; + if (isset($token->attr[$attr])) { + $subst['$CurrentAttr.Value'] = $token->attr[$attr]; + } } if (empty($args)) { @@ -69,7 +99,9 @@ class HTMLPurifier_ErrorCollector $msg = $this->locale->formatMessage($msg, $args); } - if (!empty($subst)) $msg = strtr($msg, $subst); + if (!empty($subst)) { + $msg = strtr($msg, $subst); + } // (numerically indexed) $error = array( @@ -80,16 +112,15 @@ class HTMLPurifier_ErrorCollector ); $this->_current[] = $error; - // NEW CODE BELOW ... - - $struct = null; // Top-level errors are either: // TOKEN type, if $value is set appropriately, or // "syntax" type, if $value is null $new_struct = new HTMLPurifier_ErrorStruct(); $new_struct->type = HTMLPurifier_ErrorStruct::TOKEN; - if ($token) $new_struct->value = clone $token; + if ($token) { + $new_struct->value = clone $token; + } if (is_int($line) && is_int($col)) { if (isset($this->lines[$line][$col])) { $struct = $this->lines[$line][$col]; @@ -128,30 +159,34 @@ class HTMLPurifier_ErrorCollector /** * Retrieves raw error data for custom formatter to use - * @param List of arrays in format of array(line of error, - * error severity, error message, - * recursive sub-errors array) */ - public function getRaw() { + public function getRaw() + { return $this->errors; } /** * Default HTML formatting implementation for error messages - * @param $config Configuration array, vital for HTML output nature - * @param $errors Errors array to display; used for recursion. + * @param HTMLPurifier_Config $config Configuration, vital for HTML output nature + * @param array $errors Errors array to display; used for recursion. + * @return string */ - public function getHTMLFormatted($config, $errors = null) { + public function getHTMLFormatted($config, $errors = null) + { $ret = array(); $this->generator = new HTMLPurifier_Generator($config, $this->context); - if ($errors === null) $errors = $this->errors; + if ($errors === null) { + $errors = $this->errors; + } // 'At line' message needs to be removed // generation code for new structure goes here. It needs to be recursive. foreach ($this->lines as $line => $col_array) { - if ($line == -1) continue; + if ($line == -1) { + continue; + } foreach ($col_array as $col => $struct) { $this->_renderStruct($ret, $struct, $line, $col); } @@ -168,7 +203,8 @@ class HTMLPurifier_ErrorCollector } - private function _renderStruct(&$ret, $struct, $line = null, $col = null) { + private function _renderStruct(&$ret, $struct, $line = null, $col = null) + { $stack = array($struct); $context_stack = array(array()); while ($current = array_pop($stack)) { @@ -194,7 +230,7 @@ class HTMLPurifier_ErrorCollector //$string .= '</pre>'; $ret[] = $string; } - foreach ($current->children as $type => $array) { + foreach ($current->children as $array) { $context[] = $current; $stack = array_merge($stack, array_reverse($array, true)); for ($i = count($array); $i > 0; $i--) { @@ -203,7 +239,6 @@ class HTMLPurifier_ErrorCollector } } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/ErrorStruct.php b/library/HTMLPurifier/ErrorStruct.php index 9bc8996ec..cf869d321 100644 --- a/library/HTMLPurifier/ErrorStruct.php +++ b/library/HTMLPurifier/ErrorStruct.php @@ -19,6 +19,7 @@ class HTMLPurifier_ErrorStruct /** * Type of this struct. + * @type string */ public $type; @@ -28,11 +29,13 @@ class HTMLPurifier_ErrorStruct * - TOKEN: Instance of HTMLPurifier_Token * - ATTR: array('attr-name', 'value') * - CSSPROP: array('prop-name', 'value') + * @type mixed */ public $value; /** * Errors registered for this structure. + * @type array */ public $errors = array(); @@ -40,10 +43,17 @@ class HTMLPurifier_ErrorStruct * Child ErrorStructs that are from this structure. For example, a TOKEN * ErrorStruct would contain ATTR ErrorStructs. This is a multi-dimensional * array in structure: [TYPE]['identifier'] + * @type array */ public $children = array(); - public function getChild($type, $id) { + /** + * @param string $type + * @param string $id + * @return mixed + */ + public function getChild($type, $id) + { if (!isset($this->children[$type][$id])) { $this->children[$type][$id] = new HTMLPurifier_ErrorStruct(); $this->children[$type][$id]->type = $type; @@ -51,10 +61,14 @@ class HTMLPurifier_ErrorStruct return $this->children[$type][$id]; } - public function addError($severity, $message) { + /** + * @param int $severity + * @param string $message + */ + public function addError($severity, $message) + { $this->errors[] = array($severity, $message); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Filter.php b/library/HTMLPurifier/Filter.php index 9a0e7b09f..c1f41ee16 100644 --- a/library/HTMLPurifier/Filter.php +++ b/library/HTMLPurifier/Filter.php @@ -23,24 +23,34 @@ class HTMLPurifier_Filter { /** - * Name of the filter for identification purposes + * Name of the filter for identification purposes. + * @type string */ public $name; /** * Pre-processor function, handles HTML before HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string */ - public function preFilter($html, $config, $context) { + public function preFilter($html, $config, $context) + { return $html; } /** * Post-processor function, handles HTML after HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string */ - public function postFilter($html, $config, $context) { + public function postFilter($html, $config, $context) + { return $html; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Filter/ExtractStyleBlocks.php b/library/HTMLPurifier/Filter/ExtractStyleBlocks.php index bbf78a663..08e62c16b 100644 --- a/library/HTMLPurifier/Filter/ExtractStyleBlocks.php +++ b/library/HTMLPurifier/Filter/ExtractStyleBlocks.php @@ -1,5 +1,13 @@ <?php +// why is this a top level function? Because PHP 5.2.0 doesn't seem to +// understand how to interpret this filter if it's a static method. +// It's all really silly, but if we go this route it might be reasonable +// to coalesce all of these methods into one. +function htmlpurifier_filter_extractstyleblocks_muteerrorhandler() +{ +} + /** * This filter extracts <style> blocks from input HTML, cleans them up * using CSSTidy, and then places them in $purifier->context->get('StyleBlocks') @@ -16,30 +24,77 @@ */ class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter { - + /** + * @type string + */ public $name = 'ExtractStyleBlocks'; + + /** + * @type array + */ private $_styleMatches = array(); + + /** + * @type csstidy + */ private $_tidy; - public function __construct() { + /** + * @type HTMLPurifier_AttrDef_HTML_ID + */ + private $_id_attrdef; + + /** + * @type HTMLPurifier_AttrDef_CSS_Ident + */ + private $_class_attrdef; + + /** + * @type HTMLPurifier_AttrDef_Enum + */ + private $_enum_attrdef; + + public function __construct() + { $this->_tidy = new csstidy(); + $this->_tidy->set_cfg('lowercase_s', false); + $this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true); + $this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident(); + $this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum( + array( + 'first-child', + 'link', + 'visited', + 'active', + 'hover', + 'focus' + ) + ); } /** * Save the contents of CSS blocks to style matches - * @param $matches preg_replace style $matches array + * @param array $matches preg_replace style $matches array */ - protected function styleCallback($matches) { + protected function styleCallback($matches) + { $this->_styleMatches[] = $matches[1]; } /** * Removes inline <style> tags from HTML, saves them for later use + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string * @todo Extend to indicate non-text/css style blocks */ - public function preFilter($html, $config, $context) { + public function preFilter($html, $config, $context) + { $tidy = $config->get('Filter.ExtractStyleBlocks.TidyImpl'); - if ($tidy !== null) $this->_tidy = $tidy; + if ($tidy !== null) { + $this->_tidy = $tidy; + } $html = preg_replace_callback('#<style(?:\s.*)?>(.+)</style>#isU', array($this, 'styleCallback'), $html); $style_blocks = $this->_styleMatches; $this->_styleMatches = array(); // reset @@ -55,12 +110,14 @@ class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter /** * Takes CSS (the stuff found in <style>) and cleans it. * @warning Requires CSSTidy <http://csstidy.sourceforge.net/> - * @param $css CSS styling to clean - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @return Cleaned CSS + * @param string $css CSS styling to clean + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @throws HTMLPurifier_Exception + * @return string Cleaned CSS */ - public function cleanCSS($css, $config, $context) { + public function cleanCSS($css, $config, $context) + { // prepare scope $scope = $config->get('Filter.ExtractStyleBlocks.Scope'); if ($scope !== null) { @@ -77,27 +134,170 @@ class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter $css = substr($css, 0, -3); } $css = trim($css); + set_error_handler('htmlpurifier_filter_extractstyleblocks_muteerrorhandler'); $this->_tidy->parse($css); + restore_error_handler(); $css_definition = $config->getDefinition('CSS'); + $html_definition = $config->getDefinition('HTML'); + $new_css = array(); foreach ($this->_tidy->css as $k => $decls) { // $decls are all CSS declarations inside an @ selector $new_decls = array(); foreach ($decls as $selector => $style) { $selector = trim($selector); - if ($selector === '') continue; // should not happen - if ($selector[0] === '+') { - if ($selector !== '' && $selector[0] === '+') continue; - } - if (!empty($scopes)) { - $new_selector = array(); // because multiple ones are possible - $selectors = array_map('trim', explode(',', $selector)); - foreach ($scopes as $s1) { - foreach ($selectors as $s2) { - $new_selector[] = "$s1 $s2"; + if ($selector === '') { + continue; + } // should not happen + // Parse the selector + // Here is the relevant part of the CSS grammar: + // + // ruleset + // : selector [ ',' S* selector ]* '{' ... + // selector + // : simple_selector [ combinator selector | S+ [ combinator? selector ]? ]? + // combinator + // : '+' S* + // : '>' S* + // simple_selector + // : element_name [ HASH | class | attrib | pseudo ]* + // | [ HASH | class | attrib | pseudo ]+ + // element_name + // : IDENT | '*' + // ; + // class + // : '.' IDENT + // ; + // attrib + // : '[' S* IDENT S* [ [ '=' | INCLUDES | DASHMATCH ] S* + // [ IDENT | STRING ] S* ]? ']' + // ; + // pseudo + // : ':' [ IDENT | FUNCTION S* [IDENT S*]? ')' ] + // ; + // + // For reference, here are the relevant tokens: + // + // HASH #{name} + // IDENT {ident} + // INCLUDES == + // DASHMATCH |= + // STRING {string} + // FUNCTION {ident}\( + // + // And the lexical scanner tokens + // + // name {nmchar}+ + // nmchar [_a-z0-9-]|{nonascii}|{escape} + // nonascii [\240-\377] + // escape {unicode}|\\[^\r\n\f0-9a-f] + // unicode \\{h}}{1,6}(\r\n|[ \t\r\n\f])? + // ident -?{nmstart}{nmchar*} + // nmstart [_a-z]|{nonascii}|{escape} + // string {string1}|{string2} + // string1 \"([^\n\r\f\\"]|\\{nl}|{escape})*\" + // string2 \'([^\n\r\f\\"]|\\{nl}|{escape})*\' + // + // We'll implement a subset (in order to reduce attack + // surface); in particular: + // + // - No Unicode support + // - No escapes support + // - No string support (by proxy no attrib support) + // - element_name is matched against allowed + // elements (some people might find this + // annoying...) + // - Pseudo-elements one of :first-child, :link, + // :visited, :active, :hover, :focus + + // handle ruleset + $selectors = array_map('trim', explode(',', $selector)); + $new_selectors = array(); + foreach ($selectors as $sel) { + // split on +, > and spaces + $basic_selectors = preg_split('/\s*([+> ])\s*/', $sel, -1, PREG_SPLIT_DELIM_CAPTURE); + // even indices are chunks, odd indices are + // delimiters + $nsel = null; + $delim = null; // guaranteed to be non-null after + // two loop iterations + for ($i = 0, $c = count($basic_selectors); $i < $c; $i++) { + $x = $basic_selectors[$i]; + if ($i % 2) { + // delimiter + if ($x === ' ') { + $delim = ' '; + } else { + $delim = ' ' . $x . ' '; + } + } else { + // simple selector + $components = preg_split('/([#.:])/', $x, -1, PREG_SPLIT_DELIM_CAPTURE); + $sdelim = null; + $nx = null; + for ($j = 0, $cc = count($components); $j < $cc; $j++) { + $y = $components[$j]; + if ($j === 0) { + if ($y === '*' || isset($html_definition->info[$y = strtolower($y)])) { + $nx = $y; + } else { + // $nx stays null; this matters + // if we don't manage to find + // any valid selector content, + // in which case we ignore the + // outer $delim + } + } elseif ($j % 2) { + // set delimiter + $sdelim = $y; + } else { + $attrdef = null; + if ($sdelim === '#') { + $attrdef = $this->_id_attrdef; + } elseif ($sdelim === '.') { + $attrdef = $this->_class_attrdef; + } elseif ($sdelim === ':') { + $attrdef = $this->_enum_attrdef; + } else { + throw new HTMLPurifier_Exception('broken invariant sdelim and preg_split'); + } + $r = $attrdef->validate($y, $config, $context); + if ($r !== false) { + if ($r !== true) { + $y = $r; + } + if ($nx === null) { + $nx = ''; + } + $nx .= $sdelim . $y; + } + } + } + if ($nx !== null) { + if ($nsel === null) { + $nsel = $nx; + } else { + $nsel .= $delim . $nx; + } + } else { + // delimiters to the left of invalid + // basic selector ignored + } + } + } + if ($nsel !== null) { + if (!empty($scopes)) { + foreach ($scopes as $s) { + $new_selectors[] = "$s $nsel"; + } + } else { + $new_selectors[] = $nsel; } } - $selector = implode(', ', $new_selector); // now it's a string } + if (empty($new_selectors)) { + continue; + } + $selector = implode(', ', $new_selectors); foreach ($style as $name => $value) { if (!isset($css_definition->info[$name])) { unset($style[$name]); @@ -105,15 +305,19 @@ class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter } $def = $css_definition->info[$name]; $ret = $def->validate($value, $config, $context); - if ($ret === false) unset($style[$name]); - else $style[$name] = $ret; + if ($ret === false) { + unset($style[$name]); + } else { + $style[$name] = $ret; + } } $new_decls[$selector] = $style; } - $this->_tidy->css[$k] = $new_decls; + $new_css[$k] = $new_decls; } // remove stuff that shouldn't be used, could be reenabled // after security risks are analyzed + $this->_tidy->css = $new_css; $this->_tidy->import = array(); $this->_tidy->charset = null; $this->_tidy->namespace = null; @@ -122,14 +326,13 @@ class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter // that no funny business occurs (i.e. </style> in a font-family prop). if ($config->get('Filter.ExtractStyleBlocks.Escaping')) { $css = str_replace( - array('<', '>', '&'), + array('<', '>', '&'), array('\3C ', '\3E ', '\26 '), $css ); } return $css; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Filter/YouTube.php b/library/HTMLPurifier/Filter/YouTube.php index 23df221ea..411519ad6 100644 --- a/library/HTMLPurifier/Filter/YouTube.php +++ b/library/HTMLPurifier/Filter/YouTube.php @@ -3,36 +3,62 @@ class HTMLPurifier_Filter_YouTube extends HTMLPurifier_Filter { + /** + * @type string + */ public $name = 'YouTube'; - public function preFilter($html, $config, $context) { - $pre_regex = '#<object[^>]+>.+?'. + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function preFilter($html, $config, $context) + { + $pre_regex = '#<object[^>]+>.+?' . 'http://www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?</object>#s'; $pre_replace = '<span class="youtube-embed">\1</span>'; return preg_replace($pre_regex, $pre_replace, $html); } - public function postFilter($html, $config, $context) { + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { $post_regex = '#<span class="youtube-embed">((?:v|cp)/[A-Za-z0-9\-_=]+)</span>#'; return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html); } - protected function armorUrl($url) { + /** + * @param $url + * @return string + */ + protected function armorUrl($url) + { return str_replace('--', '--', $url); } - protected function postFilterCallback($matches) { + /** + * @param array $matches + * @return string + */ + protected function postFilterCallback($matches) + { $url = $this->armorUrl($matches[1]); - return '<object width="425" height="350" type="application/x-shockwave-flash" '. - 'data="http://www.youtube.com/'.$url.'">'. - '<param name="movie" value="http://www.youtube.com/'.$url.'"></param>'. - '<!--[if IE]>'. - '<embed src="http://www.youtube.com/'.$url.'"'. - 'type="application/x-shockwave-flash"'. - 'wmode="transparent" width="425" height="350" />'. - '<![endif]-->'. - '</object>'; - + return '<object width="425" height="350" type="application/x-shockwave-flash" ' . + 'data="http://www.youtube.com/' . $url . '">' . + '<param name="movie" value="http://www.youtube.com/' . $url . '"></param>' . + '<!--[if IE]>' . + '<embed src="http://www.youtube.com/' . $url . '"' . + 'type="application/x-shockwave-flash"' . + 'wmode="transparent" width="425" height="350" />' . + '<![endif]-->' . + '</object>'; } } diff --git a/library/HTMLPurifier/Generator.php b/library/HTMLPurifier/Generator.php index 4a6241727..6fb568714 100644 --- a/library/HTMLPurifier/Generator.php +++ b/library/HTMLPurifier/Generator.php @@ -11,49 +11,64 @@ class HTMLPurifier_Generator { /** - * Whether or not generator should produce XML output + * Whether or not generator should produce XML output. + * @type bool */ private $_xhtml = true; /** - * :HACK: Whether or not generator should comment the insides of <script> tags + * :HACK: Whether or not generator should comment the insides of <script> tags. + * @type bool */ private $_scriptFix = false; /** * Cache of HTMLDefinition during HTML output to determine whether or * not attributes should be minimized. + * @type HTMLPurifier_HTMLDefinition */ private $_def; /** - * Cache of %Output.SortAttr + * Cache of %Output.SortAttr. + * @type bool */ private $_sortAttr; /** - * Cache of %Output.FlashCompat + * Cache of %Output.FlashCompat. + * @type bool */ private $_flashCompat; /** + * Cache of %Output.FixInnerHTML. + * @type bool + */ + private $_innerHTMLFix; + + /** * Stack for keeping track of object information when outputting IE * compatibility code. + * @type array */ private $_flashStack = array(); /** * Configuration for the generator + * @type HTMLPurifier_Config */ protected $config; /** - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context */ - public function __construct($config, $context) { + public function __construct($config, $context) + { $this->config = $config; $this->_scriptFix = $config->get('Output.CommentScriptContents'); + $this->_innerHTMLFix = $config->get('Output.FixInnerHTML'); $this->_sortAttr = $config->get('Output.SortAttr'); $this->_flashCompat = $config->get('Output.FlashCompat'); $this->_def = $config->getHTMLDefinition(); @@ -62,12 +77,14 @@ class HTMLPurifier_Generator /** * Generates HTML from an array of tokens. - * @param $tokens Array of HTMLPurifier_Token - * @param $config HTMLPurifier_Config object - * @return Generated HTML + * @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token + * @return string Generated HTML */ - public function generateFromTokens($tokens) { - if (!$tokens) return ''; + public function generateFromTokens($tokens) + { + if (!$tokens) { + return ''; + } // Basic algorithm $html = ''; @@ -86,30 +103,41 @@ class HTMLPurifier_Generator // Tidy cleanup if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) { $tidy = new Tidy; - $tidy->parseString($html, array( - 'indent'=> true, - 'output-xhtml' => $this->_xhtml, - 'show-body-only' => true, - 'indent-spaces' => 2, - 'wrap' => 68, - ), 'utf8'); + $tidy->parseString( + $html, + array( + 'indent'=> true, + 'output-xhtml' => $this->_xhtml, + 'show-body-only' => true, + 'indent-spaces' => 2, + 'wrap' => 68, + ), + 'utf8' + ); $tidy->cleanRepair(); $html = (string) $tidy; // explicit cast necessary } // Normalize newlines to system defined value - $nl = $this->config->get('Output.Newline'); - if ($nl === null) $nl = PHP_EOL; - if ($nl !== "\n") $html = str_replace("\n", $nl, $html); + if ($this->config->get('Core.NormalizeNewlines')) { + $nl = $this->config->get('Output.Newline'); + if ($nl === null) { + $nl = PHP_EOL; + } + if ($nl !== "\n") { + $html = str_replace("\n", $nl, $html); + } + } return $html; } /** * Generates HTML from a single token. - * @param $token HTMLPurifier_Token object. - * @return Generated HTML + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string Generated HTML */ - public function generateFromToken($token) { + public function generateFromToken($token) + { if (!$token instanceof HTMLPurifier_Token) { trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING); return ''; @@ -130,19 +158,7 @@ class HTMLPurifier_Generator $_extra = ''; if ($this->_flashCompat) { if ($token->name == "object" && !empty($this->_flashStack)) { - $flash = array_pop($this->_flashStack); - $compat_token = new HTMLPurifier_Token_Empty("embed"); - foreach ($flash->attr as $name => $val) { - if ($name == "classid") continue; - if ($name == "type") continue; - if ($name == "data") $name = "src"; - $compat_token->attr[$name] = $val; - } - foreach ($flash->param as $name => $val) { - if ($name == "movie") $name = "src"; - $compat_token->attr[$name] = $val; - } - $_extra = "<!--[if IE]>".$this->generateFromToken($compat_token)."<![endif]-->"; + // doesn't do anything for now } } return $_extra . '</' . $token->name . '>'; @@ -169,11 +185,16 @@ class HTMLPurifier_Generator /** * Special case processor for the contents of script tags + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string * @warning This runs into problems if there's already a literal * --> somewhere inside the script contents. */ - public function generateScriptFromToken($token) { - if (!$token instanceof HTMLPurifier_Token_Text) return $this->generateFromToken($token); + public function generateScriptFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token_Text) { + return $this->generateFromToken($token); + } // Thanks <http://lachy.id.au/log/2005/05/script-comments> $data = preg_replace('#//\s*$#', '', $token->data); return '<!--//--><![CDATA[//><!--' . "\n" . trim($data) . "\n" . '//--><!]]>'; @@ -182,24 +203,60 @@ class HTMLPurifier_Generator /** * Generates attribute declarations from attribute array. * @note This does not include the leading or trailing space. - * @param $assoc_array_of_attributes Attribute array - * @param $element Name of element attributes are for, used to check + * @param array $assoc_array_of_attributes Attribute array + * @param string $element Name of element attributes are for, used to check * attribute minimization. - * @return Generate HTML fragment for insertion. + * @return string Generated HTML fragment for insertion. */ - public function generateAttributes($assoc_array_of_attributes, $element = false) { + public function generateAttributes($assoc_array_of_attributes, $element = '') + { $html = ''; - if ($this->_sortAttr) ksort($assoc_array_of_attributes); + if ($this->_sortAttr) { + ksort($assoc_array_of_attributes); + } foreach ($assoc_array_of_attributes as $key => $value) { if (!$this->_xhtml) { // Remove namespaced attributes - if (strpos($key, ':') !== false) continue; + if (strpos($key, ':') !== false) { + continue; + } // Check if we should minimize the attribute: val="val" -> val if ($element && !empty($this->_def->info[$element]->attr[$key]->minimized)) { $html .= $key . ' '; continue; } } + // Workaround for Internet Explorer innerHTML bug. + // Essentially, Internet Explorer, when calculating + // innerHTML, omits quotes if there are no instances of + // angled brackets, quotes or spaces. However, when parsing + // HTML (for example, when you assign to innerHTML), it + // treats backticks as quotes. Thus, + // <img alt="``" /> + // becomes + // <img alt=`` /> + // becomes + // <img alt='' /> + // Fortunately, all we need to do is trigger an appropriate + // quoting style, which we do by adding an extra space. + // This also is consistent with the W3C spec, which states + // that user agents may ignore leading or trailing + // whitespace (in fact, most don't, at least for attributes + // like alt, but an extra space at the end is barely + // noticeable). Still, we have a configuration knob for + // this, since this transformation is not necesary if you + // don't process user input with innerHTML or you don't plan + // on supporting Internet Explorer. + if ($this->_innerHTMLFix) { + if (strpos($value, '`') !== false) { + // check if correct quoting style would not already be + // triggered + if (strcspn($value, '"\' <>') === strlen($value)) { + // protect! + $value .= ' '; + } + } + } $html .= $key.'="'.$this->escape($value).'" '; } return rtrim($html); @@ -210,15 +267,20 @@ class HTMLPurifier_Generator * @todo This really ought to be protected, but until we have a facility * for properly generating HTML here w/o using tokens, it stays * public. - * @param $string String data to escape for HTML. - * @param $quote Quoting style, like htmlspecialchars. ENT_NOQUOTES is + * @param string $string String data to escape for HTML. + * @param int $quote Quoting style, like htmlspecialchars. ENT_NOQUOTES is * permissible for non-attribute output. - * @return String escaped data. + * @return string escaped data. */ - public function escape($string, $quote = ENT_COMPAT) { + public function escape($string, $quote = null) + { + // Workaround for APC bug on Mac Leopard reported by sidepodcast + // http://htmlpurifier.org/phorum/read.php?3,4823,4846 + if ($quote === null) { + $quote = ENT_COMPAT; + } return htmlspecialchars($string, $quote, 'UTF-8'); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLDefinition.php b/library/HTMLPurifier/HTMLDefinition.php index c99ac11eb..9b7b334dd 100644 --- a/library/HTMLPurifier/HTMLDefinition.php +++ b/library/HTMLPurifier/HTMLDefinition.php @@ -29,60 +29,71 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition // FULLY-PUBLIC VARIABLES --------------------------------------------- /** - * Associative array of element names to HTMLPurifier_ElementDef + * Associative array of element names to HTMLPurifier_ElementDef. + * @type HTMLPurifier_ElementDef[] */ public $info = array(); /** * Associative array of global attribute name to attribute definition. + * @type array */ public $info_global_attr = array(); /** * String name of parent element HTML will be going into. + * @type string */ public $info_parent = 'div'; /** * Definition for parent element, allows parent element to be a * tag that's not allowed inside the HTML fragment. + * @type HTMLPurifier_ElementDef */ public $info_parent_def; /** - * String name of element used to wrap inline elements in block context + * String name of element used to wrap inline elements in block context. + * @type string * @note This is rarely used except for BLOCKQUOTEs in strict mode */ public $info_block_wrapper = 'p'; /** - * Associative array of deprecated tag name to HTMLPurifier_TagTransform + * Associative array of deprecated tag name to HTMLPurifier_TagTransform. + * @type array */ public $info_tag_transform = array(); /** * Indexed list of HTMLPurifier_AttrTransform to be performed before validation. + * @type HTMLPurifier_AttrTransform[] */ public $info_attr_transform_pre = array(); /** * Indexed list of HTMLPurifier_AttrTransform to be performed after validation. + * @type HTMLPurifier_AttrTransform[] */ public $info_attr_transform_post = array(); /** * Nested lookup array of content set name (Block, Inline) to * element name to whether or not it belongs in that content set. + * @type array */ public $info_content_sets = array(); /** * Indexed list of HTMLPurifier_Injector to be used. + * @type HTMLPurifier_Injector[] */ public $info_injector = array(); /** * Doctype object + * @type HTMLPurifier_Doctype */ public $doctype; @@ -94,12 +105,13 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition * Adds a custom attribute to a pre-existing element * @note This is strictly convenience, and does not have a corresponding * method in HTMLPurifier_HTMLModule - * @param $element_name String element name to add attribute to - * @param $attr_name String name of attribute - * @param $def Attribute definition, can be string or object, see + * @param string $element_name Element name to add attribute to + * @param string $attr_name Name of attribute + * @param mixed $def Attribute definition, can be string or object, see * HTMLPurifier_AttrTypes for details */ - public function addAttribute($element_name, $attr_name, $def) { + public function addAttribute($element_name, $attr_name, $def) + { $module = $this->getAnonymousModule(); if (!isset($module->info[$element_name])) { $element = $module->addBlankElement($element_name); @@ -111,10 +123,11 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition /** * Adds a custom element to your HTML definition - * @note See HTMLPurifier_HTMLModule::addElement for detailed + * @see HTMLPurifier_HTMLModule::addElement() for detailed * parameter and return value descriptions. */ - public function addElement($element_name, $type, $contents, $attr_collections, $attributes = array()) { + public function addElement($element_name, $type, $contents, $attr_collections, $attributes = array()) + { $module = $this->getAnonymousModule(); // assume that if the user is calling this, the element // is safe. This may not be a good idea @@ -125,10 +138,13 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition /** * Adds a blank element to your HTML definition, for overriding * existing behavior - * @note See HTMLPurifier_HTMLModule::addBlankElement for detailed + * @param string $element_name + * @return HTMLPurifier_ElementDef + * @see HTMLPurifier_HTMLModule::addBlankElement() for detailed * parameter and return value descriptions. */ - public function addBlankElement($element_name) { + public function addBlankElement($element_name) + { $module = $this->getAnonymousModule(); $element = $module->addBlankElement($element_name); return $element; @@ -138,8 +154,10 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition * Retrieves a reference to the anonymous module, so you can * bust out advanced features without having to make your own * module. + * @return HTMLPurifier_HTMLModule */ - public function getAnonymousModule() { + public function getAnonymousModule() + { if (!$this->_anonModule) { $this->_anonModule = new HTMLPurifier_HTMLModule(); $this->_anonModule->name = 'Anonymous'; @@ -147,22 +165,33 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition return $this->_anonModule; } - private $_anonModule; - + private $_anonModule = null; // PUBLIC BUT INTERNAL VARIABLES -------------------------------------- + /** + * @type string + */ public $type = 'HTML'; - public $manager; /**< Instance of HTMLPurifier_HTMLModuleManager */ + + /** + * @type HTMLPurifier_HTMLModuleManager + */ + public $manager; /** * Performs low-cost, preliminary initialization. */ - public function __construct() { + public function __construct() + { $this->manager = new HTMLPurifier_HTMLModuleManager(); } - protected function doSetup($config) { + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetup($config) + { $this->processModules($config); $this->setupConfigStuff($config); unset($this->manager); @@ -176,9 +205,10 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition /** * Extract out the information from the manager + * @param HTMLPurifier_Config $config */ - protected function processModules($config) { - + protected function processModules($config) + { if ($this->_anonModule) { // for user specific changes // this is late-loaded so we don't have to deal with PHP4 @@ -191,40 +221,53 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition $this->doctype = $this->manager->doctype; foreach ($this->manager->modules as $module) { - foreach($module->info_tag_transform as $k => $v) { - if ($v === false) unset($this->info_tag_transform[$k]); - else $this->info_tag_transform[$k] = $v; + foreach ($module->info_tag_transform as $k => $v) { + if ($v === false) { + unset($this->info_tag_transform[$k]); + } else { + $this->info_tag_transform[$k] = $v; + } } - foreach($module->info_attr_transform_pre as $k => $v) { - if ($v === false) unset($this->info_attr_transform_pre[$k]); - else $this->info_attr_transform_pre[$k] = $v; + foreach ($module->info_attr_transform_pre as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_pre[$k]); + } else { + $this->info_attr_transform_pre[$k] = $v; + } } - foreach($module->info_attr_transform_post as $k => $v) { - if ($v === false) unset($this->info_attr_transform_post[$k]); - else $this->info_attr_transform_post[$k] = $v; + foreach ($module->info_attr_transform_post as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_post[$k]); + } else { + $this->info_attr_transform_post[$k] = $v; + } } foreach ($module->info_injector as $k => $v) { - if ($v === false) unset($this->info_injector[$k]); - else $this->info_injector[$k] = $v; + if ($v === false) { + unset($this->info_injector[$k]); + } else { + $this->info_injector[$k] = $v; + } } } - $this->info = $this->manager->getElements(); $this->info_content_sets = $this->manager->contentSets->lookup; - } /** * Sets up stuff based on config. We need a better way of doing this. + * @param HTMLPurifier_Config $config */ - protected function setupConfigStuff($config) { - + protected function setupConfigStuff($config) + { $block_wrapper = $config->get('HTML.BlockWrapper'); if (isset($this->info_content_sets['Block'][$block_wrapper])) { $this->info_block_wrapper = $block_wrapper; } else { - trigger_error('Cannot use non-block element as block wrapper', - E_USER_ERROR); + trigger_error( + 'Cannot use non-block element as block wrapper', + E_USER_ERROR + ); } $parent = $config->get('HTML.Parent'); @@ -233,14 +276,15 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition $this->info_parent = $parent; $this->info_parent_def = $def; } else { - trigger_error('Cannot use unrecognized element as parent', - E_USER_ERROR); + trigger_error( + 'Cannot use unrecognized element as parent', + E_USER_ERROR + ); $this->info_parent_def = $this->manager->getElement($this->info_parent, true); } // support template text - $support = "(for information on implementing this, see the ". - "support forums) "; + $support = "(for information on implementing this, see the support forums) "; // setup allowed elements ----------------------------------------- @@ -256,7 +300,9 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition if (is_array($allowed_elements)) { foreach ($this->info as $name => $d) { - if(!isset($allowed_elements[$name])) unset($this->info[$name]); + if (!isset($allowed_elements[$name])) { + unset($this->info[$name]); + } unset($allowed_elements[$name]); } // emit errors @@ -270,7 +316,6 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition $allowed_attributes_mutable = $allowed_attributes; // by copy! if (is_array($allowed_attributes)) { - // This actually doesn't do anything, since we went away from // global attributes. It's possible that userland code uses // it, but HTMLModuleManager doesn't! @@ -285,7 +330,9 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition unset($allowed_attributes_mutable[$key]); } } - if ($delete) unset($this->info_global_attr[$attr]); + if ($delete) { + unset($this->info_global_attr[$attr]); + } } foreach ($this->info as $tag => $info) { @@ -300,7 +347,16 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition unset($allowed_attributes_mutable[$key]); } } - if ($delete) unset($this->info[$tag]->attr[$attr]); + if ($delete) { + if ($this->info[$tag]->attr[$attr]->required) { + trigger_error( + "Required attribute '$attr' in element '$tag' " . + "was not allowed, which means '$tag' will not be allowed either", + E_USER_WARNING + ); + } + unset($this->info[$tag]->attr[$attr]); + } } } // emit errors @@ -313,23 +369,29 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition $element = htmlspecialchars($bits[0]); $attribute = htmlspecialchars($bits[1]); if (!isset($this->info[$element])) { - trigger_error("Cannot allow attribute '$attribute' if element '$element' is not allowed/supported $support"); + trigger_error( + "Cannot allow attribute '$attribute' if element " . + "'$element' is not allowed/supported $support" + ); } else { - trigger_error("Attribute '$attribute' in element '$element' not supported $support", - E_USER_WARNING); + trigger_error( + "Attribute '$attribute' in element '$element' not supported $support", + E_USER_WARNING + ); } break; } // otherwise fall through case 1: $attribute = htmlspecialchars($bits[0]); - trigger_error("Global attribute '$attribute' is not ". + trigger_error( + "Global attribute '$attribute' is not ". "supported in any elements $support", - E_USER_WARNING); + E_USER_WARNING + ); break; } } - } // setup forbidden elements --------------------------------------- @@ -343,25 +405,34 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition continue; } foreach ($info->attr as $attr => $x) { - if ( - isset($forbidden_attributes["$tag@$attr"]) || + if (isset($forbidden_attributes["$tag@$attr"]) || isset($forbidden_attributes["*@$attr"]) || isset($forbidden_attributes[$attr]) ) { unset($this->info[$tag]->attr[$attr]); continue; - } // this segment might get removed eventually - elseif (isset($forbidden_attributes["$tag.$attr"])) { + } elseif (isset($forbidden_attributes["$tag.$attr"])) { // this segment might get removed eventually // $tag.$attr are not user supplied, so no worries! - trigger_error("Error with $tag.$attr: tag.attr syntax not supported for HTML.ForbiddenAttributes; use tag@attr instead", E_USER_WARNING); + trigger_error( + "Error with $tag.$attr: tag.attr syntax not supported for " . + "HTML.ForbiddenAttributes; use tag@attr instead", + E_USER_WARNING + ); } } } foreach ($forbidden_attributes as $key => $v) { - if (strlen($key) < 2) continue; - if ($key[0] != '*') continue; + if (strlen($key) < 2) { + continue; + } + if ($key[0] != '*') { + continue; + } if ($key[1] == '.') { - trigger_error("Error with $key: *.attr syntax not supported for HTML.ForbiddenAttributes; use attr instead", E_USER_WARNING); + trigger_error( + "Error with $key: *.attr syntax not supported for HTML.ForbiddenAttributes; use attr instead", + E_USER_WARNING + ); } } @@ -380,12 +451,12 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition * separate lists for processing. Format is element[attr1|attr2],element2... * @warning Although it's largely drawn from TinyMCE's implementation, * it is different, and you'll probably have to modify your lists - * @param $list String list to parse - * @param array($allowed_elements, $allowed_attributes) + * @param array $list String list to parse + * @return array * @todo Give this its own class, probably static interface */ - public function parseTinyMCEAllowedList($list) { - + public function parseTinyMCEAllowedList($list) + { $list = str_replace(array(' ', "\t"), '', $list); $elements = array(); @@ -393,7 +464,9 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition $chunks = preg_split('/(,|[\n\r]+)/', $list); foreach ($chunks as $chunk) { - if (empty($chunk)) continue; + if (empty($chunk)) { + continue; + } // remove TinyMCE element control characters if (!strpos($chunk, '[')) { $element = $chunk; @@ -401,20 +474,20 @@ class HTMLPurifier_HTMLDefinition extends HTMLPurifier_Definition } else { list($element, $attr) = explode('[', $chunk); } - if ($element !== '*') $elements[$element] = true; - if (!$attr) continue; + if ($element !== '*') { + $elements[$element] = true; + } + if (!$attr) { + continue; + } $attr = substr($attr, 0, strlen($attr) - 1); // remove trailing ] $attr = explode('|', $attr); foreach ($attr as $key) { $attributes["$element.$key"] = true; } } - return array($elements, $attributes); - } - - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule.php b/library/HTMLPurifier/HTMLModule.php index 072cf6808..bb3a9230b 100644 --- a/library/HTMLPurifier/HTMLModule.php +++ b/library/HTMLPurifier/HTMLModule.php @@ -21,13 +21,15 @@ class HTMLPurifier_HTMLModule // -- Overloadable ---------------------------------------------------- /** - * Short unique string identifier of the module + * Short unique string identifier of the module. + * @type string */ public $name; /** - * Informally, a list of elements this module changes. Not used in - * any significant way. + * Informally, a list of elements this module changes. + * Not used in any significant way. + * @type array */ public $elements = array(); @@ -35,6 +37,7 @@ class HTMLPurifier_HTMLModule * Associative array of element names to element definitions. * Some definitions may be incomplete, to be merged in later * with the full definition. + * @type array */ public $info = array(); @@ -43,6 +46,7 @@ class HTMLPurifier_HTMLModule * This is commonly used to, say, add an A element to the Inline * content set. This corresponds to an internal variable $content_sets * and NOT info_content_sets member variable of HTMLDefinition. + * @type array */ public $content_sets = array(); @@ -53,21 +57,25 @@ class HTMLPurifier_HTMLModule * the style attribute to the Core. Corresponds to HTMLDefinition's * attr_collections->info, since the object's data is only info, * with extra behavior associated with it. + * @type array */ public $attr_collections = array(); /** - * Associative array of deprecated tag name to HTMLPurifier_TagTransform + * Associative array of deprecated tag name to HTMLPurifier_TagTransform. + * @type array */ public $info_tag_transform = array(); /** * List of HTMLPurifier_AttrTransform to be performed before validation. + * @type array */ public $info_attr_transform_pre = array(); /** * List of HTMLPurifier_AttrTransform to be performed after validation. + * @type array */ public $info_attr_transform_post = array(); @@ -76,6 +84,7 @@ class HTMLPurifier_HTMLModule * An injector will only be invoked if all of it's pre-requisites are met; * if an injector fails setup, there will be no error; it will simply be * silently disabled. + * @type array */ public $info_injector = array(); @@ -84,6 +93,7 @@ class HTMLPurifier_HTMLModule * For optimization reasons: may save a call to a function. Be sure * to set it if you do implement getChildDef(), otherwise it will have * no effect! + * @type bool */ public $defines_child_def = false; @@ -94,6 +104,7 @@ class HTMLPurifier_HTMLModule * which is based off of safe HTML, to explicitly say, "This is safe," even * though there are modules which are "unsafe") * + * @type bool * @note Previously, safety could be applied at an element level granularity. * We've removed this ability, so in order to add "unsafe" elements * or attributes, a dedicated module with this property set to false @@ -106,51 +117,62 @@ class HTMLPurifier_HTMLModule * content_model and content_model_type member variables of * the HTMLPurifier_ElementDef class. There is a similar function * in HTMLPurifier_HTMLDefinition. - * @param $def HTMLPurifier_ElementDef instance + * @param HTMLPurifier_ElementDef $def * @return HTMLPurifier_ChildDef subclass */ - public function getChildDef($def) {return false;} + public function getChildDef($def) + { + return false; + } // -- Convenience ----------------------------------------------------- /** * Convenience function that sets up a new element - * @param $element Name of element to add - * @param $type What content set should element be registered to? + * @param string $element Name of element to add + * @param string|bool $type What content set should element be registered to? * Set as false to skip this step. - * @param $contents Allowed children in form of: + * @param string $contents Allowed children in form of: * "$content_model_type: $content_model" - * @param $attr_includes What attribute collections to register to + * @param array $attr_includes What attribute collections to register to * element? - * @param $attr What unique attributes does the element define? - * @note See ElementDef for in-depth descriptions of these parameters. - * @return Created element definition object, so you + * @param array $attr What unique attributes does the element define? + * @see HTMLPurifier_ElementDef:: for in-depth descriptions of these parameters. + * @return HTMLPurifier_ElementDef Created element definition object, so you * can set advanced parameters */ - public function addElement($element, $type, $contents, $attr_includes = array(), $attr = array()) { + public function addElement($element, $type, $contents, $attr_includes = array(), $attr = array()) + { $this->elements[] = $element; // parse content_model list($content_model_type, $content_model) = $this->parseContents($contents); // merge in attribute inclusions $this->mergeInAttrIncludes($attr, $attr_includes); // add element to content sets - if ($type) $this->addElementToContentSet($element, $type); + if ($type) { + $this->addElementToContentSet($element, $type); + } // create element $this->info[$element] = HTMLPurifier_ElementDef::create( - $content_model, $content_model_type, $attr + $content_model, + $content_model_type, + $attr ); // literal object $contents means direct child manipulation - if (!is_string($contents)) $this->info[$element]->child = $contents; + if (!is_string($contents)) { + $this->info[$element]->child = $contents; + } return $this->info[$element]; } /** * Convenience function that creates a totally blank, non-standalone * element. - * @param $element Name of element to create - * @return Created element + * @param string $element Name of element to create + * @return HTMLPurifier_ElementDef Created element */ - public function addBlankElement($element) { + public function addBlankElement($element) + { if (!isset($this->info[$element])) { $this->elements[] = $element; $this->info[$element] = new HTMLPurifier_ElementDef(); @@ -163,27 +185,35 @@ class HTMLPurifier_HTMLModule /** * Convenience function that registers an element to a content set - * @param Element to register - * @param Name content set (warning: case sensitive, usually upper-case + * @param string $element Element to register + * @param string $type Name content set (warning: case sensitive, usually upper-case * first letter) */ - public function addElementToContentSet($element, $type) { - if (!isset($this->content_sets[$type])) $this->content_sets[$type] = ''; - else $this->content_sets[$type] .= ' | '; + public function addElementToContentSet($element, $type) + { + if (!isset($this->content_sets[$type])) { + $this->content_sets[$type] = ''; + } else { + $this->content_sets[$type] .= ' | '; + } $this->content_sets[$type] .= $element; } /** * Convenience function that transforms single-string contents * into separate content model and content model type - * @param $contents Allowed children in form of: + * @param string $contents Allowed children in form of: * "$content_model_type: $content_model" + * @return array * @note If contents is an object, an array of two nulls will be * returned, and the callee needs to take the original $contents * and use it directly. */ - public function parseContents($contents) { - if (!is_string($contents)) return array(null, null); // defer + public function parseContents($contents) + { + if (!is_string($contents)) { + return array(null, null); + } // defer switch ($contents) { // check for shorthand content model forms case 'Empty': @@ -202,13 +232,17 @@ class HTMLPurifier_HTMLModule /** * Convenience function that merges a list of attribute includes into * an attribute array. - * @param $attr Reference to attr array to modify - * @param $attr_includes Array of includes / string include to merge in + * @param array $attr Reference to attr array to modify + * @param array $attr_includes Array of includes / string include to merge in */ - public function mergeInAttrIncludes(&$attr, $attr_includes) { + public function mergeInAttrIncludes(&$attr, $attr_includes) + { if (!is_array($attr_includes)) { - if (empty($attr_includes)) $attr_includes = array(); - else $attr_includes = array($attr_includes); + if (empty($attr_includes)) { + $attr_includes = array(); + } else { + $attr_includes = array($attr_includes); + } } $attr[0] = $attr_includes; } @@ -216,16 +250,21 @@ class HTMLPurifier_HTMLModule /** * Convenience function that generates a lookup table with boolean * true as value. - * @param $list List of values to turn into a lookup + * @param string $list List of values to turn into a lookup * @note You can also pass an arbitrary number of arguments in * place of the regular argument - * @return Lookup array equivalent of list + * @return array array equivalent of list */ - public function makeLookup($list) { - if (is_string($list)) $list = func_get_args(); + public function makeLookup($list) + { + if (is_string($list)) { + $list = func_get_args(); + } $ret = array(); foreach ($list as $value) { - if (is_null($value)) continue; + if (is_null($value)) { + continue; + } $ret[$value] = true; } return $ret; @@ -235,10 +274,11 @@ class HTMLPurifier_HTMLModule * Lazy load construction of the module after determining whether * or not it's needed, and also when a finalized configuration object * is available. - * @param $config Instance of HTMLPurifier_Config + * @param HTMLPurifier_Config $config */ - public function setup($config) {} - + public function setup($config) + { + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Bdo.php b/library/HTMLPurifier/HTMLModule/Bdo.php index 3d66f1b4e..1e67c790d 100644 --- a/library/HTMLPurifier/HTMLModule/Bdo.php +++ b/library/HTMLPurifier/HTMLModule/Bdo.php @@ -7,25 +7,38 @@ class HTMLPurifier_HTMLModule_Bdo extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Bdo'; + + /** + * @type array + */ public $attr_collections = array( 'I18N' => array('dir' => false) ); - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $bdo = $this->addElement( - 'bdo', 'Inline', 'Inline', array('Core', 'Lang'), + 'bdo', + 'Inline', + 'Inline', + array('Core', 'Lang'), array( 'dir' => 'Enum#ltr,rtl', // required // The Abstract Module specification has the attribute // inclusions wrong for bdo: bdo allows Lang ) ); - $bdo->attr_transform_post['required-dir'] = new HTMLPurifier_AttrTransform_BdoDir(); + $bdo->attr_transform_post[] = new HTMLPurifier_AttrTransform_BdoDir(); $this->attr_collections['I18N']['dir'] = 'Enum#ltr,rtl'; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/CommonAttributes.php b/library/HTMLPurifier/HTMLModule/CommonAttributes.php index 7c15da84f..a96ab1bef 100644 --- a/library/HTMLPurifier/HTMLModule/CommonAttributes.php +++ b/library/HTMLPurifier/HTMLModule/CommonAttributes.php @@ -2,8 +2,14 @@ class HTMLPurifier_HTMLModule_CommonAttributes extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'CommonAttributes'; + /** + * @type array + */ public $attr_collections = array( 'Core' => array( 0 => array('Style'), @@ -20,7 +26,6 @@ class HTMLPurifier_HTMLModule_CommonAttributes extends HTMLPurifier_HTMLModule 0 => array('Core', 'I18N') ) ); - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Edit.php b/library/HTMLPurifier/HTMLModule/Edit.php index ff9369055..a9042a357 100644 --- a/library/HTMLPurifier/HTMLModule/Edit.php +++ b/library/HTMLPurifier/HTMLModule/Edit.php @@ -7,9 +7,16 @@ class HTMLPurifier_HTMLModule_Edit extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Edit'; - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $contents = 'Chameleon: #PCDATA | Inline ! #PCDATA | Flow'; $attr = array( 'cite' => 'URI', @@ -26,13 +33,23 @@ class HTMLPurifier_HTMLModule_Edit extends HTMLPurifier_HTMLModule // Inline context ! Block context (exclamation mark is // separator, see getChildDef for parsing) + /** + * @type bool + */ public $defines_child_def = true; - public function getChildDef($def) { - if ($def->content_model_type != 'chameleon') return false; + + /** + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef_Chameleon + */ + public function getChildDef($def) + { + if ($def->content_model_type != 'chameleon') { + return false; + } $value = explode('!', $def->content_model); return new HTMLPurifier_ChildDef_Chameleon($value[0], $value[1]); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Forms.php b/library/HTMLPurifier/HTMLModule/Forms.php index 44c22f6f8..6f7ddbc05 100644 --- a/library/HTMLPurifier/HTMLModule/Forms.php +++ b/library/HTMLPurifier/HTMLModule/Forms.php @@ -5,86 +5,142 @@ */ class HTMLPurifier_HTMLModule_Forms extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Forms'; + + /** + * @type bool + */ public $safe = false; + /** + * @type array + */ public $content_sets = array( 'Block' => 'Form', 'Inline' => 'Formctrl', ); - public function setup($config) { - $form = $this->addElement('form', 'Form', - 'Required: Heading | List | Block | fieldset', 'Common', array( - 'accept' => 'ContentTypes', - 'accept-charset' => 'Charsets', - 'action*' => 'URI', - 'method' => 'Enum#get,post', - // really ContentType, but these two are the only ones used today - 'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data', - )); + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $form = $this->addElement( + 'form', + 'Form', + 'Required: Heading | List | Block | fieldset', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accept-charset' => 'Charsets', + 'action*' => 'URI', + 'method' => 'Enum#get,post', + // really ContentType, but these two are the only ones used today + 'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data', + ) + ); $form->excludes = array('form' => true); - $input = $this->addElement('input', 'Formctrl', 'Empty', 'Common', array( - 'accept' => 'ContentTypes', - 'accesskey' => 'Character', - 'alt' => 'Text', - 'checked' => 'Bool#checked', - 'disabled' => 'Bool#disabled', - 'maxlength' => 'Number', - 'name' => 'CDATA', - 'readonly' => 'Bool#readonly', - 'size' => 'Number', - 'src' => 'URI#embeds', - 'tabindex' => 'Number', - 'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image', - 'value' => 'CDATA', - )); + $input = $this->addElement( + 'input', + 'Formctrl', + 'Empty', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accesskey' => 'Character', + 'alt' => 'Text', + 'checked' => 'Bool#checked', + 'disabled' => 'Bool#disabled', + 'maxlength' => 'Number', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'size' => 'Number', + 'src' => 'URI#embedded', + 'tabindex' => 'Number', + 'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image', + 'value' => 'CDATA', + ) + ); $input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input(); - $this->addElement('select', 'Formctrl', 'Required: optgroup | option', 'Common', array( - 'disabled' => 'Bool#disabled', - 'multiple' => 'Bool#multiple', - 'name' => 'CDATA', - 'size' => 'Number', - 'tabindex' => 'Number', - )); - - $this->addElement('option', false, 'Optional: #PCDATA', 'Common', array( - 'disabled' => 'Bool#disabled', - 'label' => 'Text', - 'selected' => 'Bool#selected', - 'value' => 'CDATA', - )); + $this->addElement( + 'select', + 'Formctrl', + 'Required: optgroup | option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'multiple' => 'Bool#multiple', + 'name' => 'CDATA', + 'size' => 'Number', + 'tabindex' => 'Number', + ) + ); + + $this->addElement( + 'option', + false, + 'Optional: #PCDATA', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label' => 'Text', + 'selected' => 'Bool#selected', + 'value' => 'CDATA', + ) + ); // It's illegal for there to be more than one selected, but not // be multiple. Also, no selected means undefined behavior. This might // be difficult to implement; perhaps an injector, or a context variable. - $textarea = $this->addElement('textarea', 'Formctrl', 'Optional: #PCDATA', 'Common', array( - 'accesskey' => 'Character', - 'cols*' => 'Number', - 'disabled' => 'Bool#disabled', - 'name' => 'CDATA', - 'readonly' => 'Bool#readonly', - 'rows*' => 'Number', - 'tabindex' => 'Number', - )); + $textarea = $this->addElement( + 'textarea', + 'Formctrl', + 'Optional: #PCDATA', + 'Common', + array( + 'accesskey' => 'Character', + 'cols*' => 'Number', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'rows*' => 'Number', + 'tabindex' => 'Number', + ) + ); $textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea(); - $button = $this->addElement('button', 'Formctrl', 'Optional: #PCDATA | Heading | List | Block | Inline', 'Common', array( - 'accesskey' => 'Character', - 'disabled' => 'Bool#disabled', - 'name' => 'CDATA', - 'tabindex' => 'Number', - 'type' => 'Enum#button,submit,reset', - 'value' => 'CDATA', - )); + $button = $this->addElement( + 'button', + 'Formctrl', + 'Optional: #PCDATA | Heading | List | Block | Inline', + 'Common', + array( + 'accesskey' => 'Character', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'tabindex' => 'Number', + 'type' => 'Enum#button,submit,reset', + 'value' => 'CDATA', + ) + ); // For exclusions, ideally we'd specify content sets, not literal elements $button->excludes = $this->makeLookup( - 'form', 'fieldset', // Form - 'input', 'select', 'textarea', 'label', 'button', // Formctrl - 'a' // as per HTML 4.01 spec, this is omitted by modularization + 'form', + 'fieldset', // Form + 'input', + 'select', + 'textarea', + 'label', + 'button', // Formctrl + 'a', // as per HTML 4.01 spec, this is omitted by modularization + 'isindex', + 'iframe' // legacy items ); // Extra exclusion: img usemap="" is not permitted within this element. @@ -94,24 +150,40 @@ class HTMLPurifier_HTMLModule_Forms extends HTMLPurifier_HTMLModule // This is HIGHLY user-unfriendly; we need a custom child-def for this $this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common'); - $label = $this->addElement('label', 'Formctrl', 'Optional: #PCDATA | Inline', 'Common', array( - 'accesskey' => 'Character', - // 'for' => 'IDREF', // IDREF not implemented, cannot allow - )); + $label = $this->addElement( + 'label', + 'Formctrl', + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + // 'for' => 'IDREF', // IDREF not implemented, cannot allow + ) + ); $label->excludes = array('label' => true); - $this->addElement('legend', false, 'Optional: #PCDATA | Inline', 'Common', array( - 'accesskey' => 'Character', - )); - - $this->addElement('optgroup', false, 'Required: option', 'Common', array( - 'disabled' => 'Bool#disabled', - 'label*' => 'Text', - )); + $this->addElement( + 'legend', + false, + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + ) + ); + $this->addElement( + 'optgroup', + false, + 'Required: option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label*' => 'Text', + ) + ); // Don't forget an injector for <isindex>. This one's a little complex // because it maps to multiple elements. - } } diff --git a/library/HTMLPurifier/HTMLModule/Hypertext.php b/library/HTMLPurifier/HTMLModule/Hypertext.php index d7e9bdd27..72d7a31e6 100644 --- a/library/HTMLPurifier/HTMLModule/Hypertext.php +++ b/library/HTMLPurifier/HTMLModule/Hypertext.php @@ -6,11 +6,21 @@ class HTMLPurifier_HTMLModule_Hypertext extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Hypertext'; - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $a = $this->addElement( - 'a', 'Inline', 'Inline', 'Common', + 'a', + 'Inline', + 'Inline', + 'Common', array( // 'accesskey' => 'Character', // 'charset' => 'Charset', @@ -25,7 +35,6 @@ class HTMLPurifier_HTMLModule_Hypertext extends HTMLPurifier_HTMLModule $a->formatting = true; $a->excludes = array('a' => true); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Iframe.php b/library/HTMLPurifier/HTMLModule/Iframe.php new file mode 100644 index 000000000..f7e7c91c0 --- /dev/null +++ b/library/HTMLPurifier/HTMLModule/Iframe.php @@ -0,0 +1,51 @@ +<?php + +/** + * XHTML 1.1 Iframe Module provides inline frames. + * + * @note This module is not considered safe unless an Iframe + * whitelisting mechanism is specified. Currently, the only + * such mechanism is %URL.SafeIframeRegexp + */ +class HTMLPurifier_HTMLModule_Iframe extends HTMLPurifier_HTMLModule +{ + + /** + * @type string + */ + public $name = 'Iframe'; + + /** + * @type bool + */ + public $safe = false; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + if ($config->get('HTML.SafeIframe')) { + $this->safe = true; + } + $this->addElement( + 'iframe', + 'Inline', + 'Flow', + 'Common', + array( + 'src' => 'URI#embedded', + 'width' => 'Length', + 'height' => 'Length', + 'name' => 'ID', + 'scrolling' => 'Enum#yes,no,auto', + 'frameborder' => 'Enum#0,1', + 'longdesc' => 'URI', + 'marginheight' => 'Pixels', + 'marginwidth' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Image.php b/library/HTMLPurifier/HTMLModule/Image.php index 948d435bc..0f5fdb3ba 100644 --- a/library/HTMLPurifier/HTMLModule/Image.php +++ b/library/HTMLPurifier/HTMLModule/Image.php @@ -8,18 +8,28 @@ class HTMLPurifier_HTMLModule_Image extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Image'; - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $max = $config->get('HTML.MaxImgLength'); $img = $this->addElement( - 'img', 'Inline', 'Empty', 'Common', + 'img', + 'Inline', + 'Empty', + 'Common', array( 'alt*' => 'Text', // According to the spec, it's Length, but percents can // be abused, so we allow only Pixels. 'height' => 'Pixels#' . $max, - 'width' => 'Pixels#' . $max, + 'width' => 'Pixels#' . $max, 'longdesc' => 'URI', 'src*' => new HTMLPurifier_AttrDef_URI(true), // embedded ) @@ -34,7 +44,6 @@ class HTMLPurifier_HTMLModule_Image extends HTMLPurifier_HTMLModule $img->attr_transform_post[] = new HTMLPurifier_AttrTransform_ImgRequired(); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Legacy.php b/library/HTMLPurifier/HTMLModule/Legacy.php index df33927ba..86b529957 100644 --- a/library/HTMLPurifier/HTMLModule/Legacy.php +++ b/library/HTMLPurifier/HTMLModule/Legacy.php @@ -18,29 +18,58 @@ class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Legacy'; - public function setup($config) { - - $this->addElement('basefont', 'Inline', 'Empty', false, array( - 'color' => 'Color', - 'face' => 'Text', // extremely broad, we should - 'size' => 'Text', // tighten it - 'id' => 'ID' - )); + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'basefont', + 'Inline', + 'Empty', + null, + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + 'id' => 'ID' + ) + ); $this->addElement('center', 'Block', 'Flow', 'Common'); - $this->addElement('dir', 'Block', 'Required: li', 'Common', array( - 'compact' => 'Bool#compact' - )); - $this->addElement('font', 'Inline', 'Inline', array('Core', 'I18N'), array( - 'color' => 'Color', - 'face' => 'Text', // extremely broad, we should - 'size' => 'Text', // tighten it - )); - $this->addElement('menu', 'Block', 'Required: li', 'Common', array( - 'compact' => 'Bool#compact' - )); + $this->addElement( + 'dir', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + $this->addElement( + 'font', + 'Inline', + 'Inline', + array('Core', 'I18N'), + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + ) + ); + $this->addElement( + 'menu', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); $s = $this->addElement('s', 'Inline', 'Inline', 'Common'); $s->formatting = true; @@ -89,7 +118,7 @@ class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule $hr->attr['width'] = 'Length'; $img = $this->addBlankElement('img'); - $img->attr['align'] = 'Enum#top,middle,bottom,left,right'; + $img->attr['align'] = 'IAlign'; $img->attr['border'] = 'Pixels'; $img->attr['hspace'] = 'Pixels'; $img->attr['vspace'] = 'Pixels'; @@ -98,7 +127,7 @@ class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule $li = $this->addBlankElement('li'); $li->attr['value'] = new HTMLPurifier_AttrDef_Integer(); - $li->attr['type'] = 'Enum#s:1,i,I,a,A,disc,square,circle'; + $li->attr['type'] = 'Enum#s:1,i,I,a,A,disc,square,circle'; $ol = $this->addBlankElement('ol'); $ol->attr['compact'] = 'Bool#compact'; @@ -136,8 +165,22 @@ class HTMLPurifier_HTMLModule_Legacy extends HTMLPurifier_HTMLModule $ul->attr['compact'] = 'Bool#compact'; $ul->attr['type'] = 'Enum#square,disc,circle'; - } + // "safe" modifications to "unsafe" elements + // WARNING: If you want to add support for an unsafe, legacy + // attribute, make a new TrustedLegacy module with the trusted + // bit set appropriately + $form = $this->addBlankElement('form'); + $form->content_model = 'Flow | #PCDATA'; + $form->content_model_type = 'optional'; + $form->attr['target'] = 'FrameTarget'; + + $input = $this->addBlankElement('input'); + $input->attr['align'] = 'IAlign'; + + $legend = $this->addBlankElement('legend'); + $legend->attr['align'] = 'LAlign'; + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/List.php b/library/HTMLPurifier/HTMLModule/List.php index 74d4522f4..7a20ff701 100644 --- a/library/HTMLPurifier/HTMLModule/List.php +++ b/library/HTMLPurifier/HTMLModule/List.php @@ -5,7 +5,9 @@ */ class HTMLPurifier_HTMLModule_List extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'List'; // According to the abstract schema, the List content set is a fully formed @@ -17,13 +19,26 @@ class HTMLPurifier_HTMLModule_List extends HTMLPurifier_HTMLModule // we don't have support for such nested expressions without using // the incredibly inefficient and draconic Custom ChildDef. + /** + * @type array + */ public $content_sets = array('Flow' => 'List'); - public function setup($config) { - $ol = $this->addElement('ol', 'List', 'Required: li', 'Common'); - $ol->wrap = "li"; - $ul = $this->addElement('ul', 'List', 'Required: li', 'Common'); - $ul->wrap = "li"; + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $ol = $this->addElement('ol', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + $ul = $this->addElement('ul', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + // XXX The wrap attribute is handled by MakeWellFormed. This is all + // quite unsatisfactory, because we generated this + // *specifically* for lists, and now a big chunk of the handling + // is done properly by the List ChildDef. So actually, we just + // want enough information to make autoclosing work properly, + // and then hand off the tricky stuff to the ChildDef. + $ol->wrap = 'li'; + $ul->wrap = 'li'; $this->addElement('dl', 'List', 'Required: dt | dd', 'Common'); $this->addElement('li', false, 'Flow', 'Common'); @@ -31,7 +46,6 @@ class HTMLPurifier_HTMLModule_List extends HTMLPurifier_HTMLModule $this->addElement('dd', false, 'Flow', 'Common'); $this->addElement('dt', false, 'Inline', 'Common'); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Name.php b/library/HTMLPurifier/HTMLModule/Name.php index 05694b450..60c054515 100644 --- a/library/HTMLPurifier/HTMLModule/Name.php +++ b/library/HTMLPurifier/HTMLModule/Name.php @@ -2,20 +2,25 @@ class HTMLPurifier_HTMLModule_Name extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Name'; - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $elements = array('a', 'applet', 'form', 'frame', 'iframe', 'img', 'map'); foreach ($elements as $name) { $element = $this->addBlankElement($name); $element->attr['name'] = 'CDATA'; if (!$config->get('HTML.Attr.Name.UseCDATA')) { - $element->attr_transform_post['NameSync'] = new HTMLPurifier_AttrTransform_NameSync(); + $element->attr_transform_post[] = new HTMLPurifier_AttrTransform_NameSync(); } } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Nofollow.php b/library/HTMLPurifier/HTMLModule/Nofollow.php new file mode 100644 index 000000000..dc9410a89 --- /dev/null +++ b/library/HTMLPurifier/HTMLModule/Nofollow.php @@ -0,0 +1,25 @@ +<?php + +/** + * Module adds the nofollow attribute transformation to a tags. It + * is enabled by HTML.Nofollow + */ +class HTMLPurifier_HTMLModule_Nofollow extends HTMLPurifier_HTMLModule +{ + + /** + * @type string + */ + public $name = 'Nofollow'; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $a = $this->addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_Nofollow(); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php b/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php index 5f1b14abb..da722253a 100644 --- a/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php +++ b/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php @@ -2,8 +2,14 @@ class HTMLPurifier_HTMLModule_NonXMLCommonAttributes extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'NonXMLCommonAttributes'; + /** + * @type array + */ public $attr_collections = array( 'Lang' => array( 'lang' => 'LanguageCode', diff --git a/library/HTMLPurifier/HTMLModule/Object.php b/library/HTMLPurifier/HTMLModule/Object.php index 193c1011f..2f9efc5c8 100644 --- a/library/HTMLPurifier/HTMLModule/Object.php +++ b/library/HTMLPurifier/HTMLModule/Object.php @@ -7,13 +7,26 @@ */ class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Object'; - public $safe = false; - public function setup($config) { + /** + * @type bool + */ + public $safe = false; - $this->addElement('object', 'Inline', 'Optional: #PCDATA | Flow | param', 'Common', + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'object', + 'Inline', + 'Optional: #PCDATA | Flow | param', + 'Common', array( 'archive' => 'URI', 'classid' => 'URI', @@ -30,18 +43,20 @@ class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule ) ); - $this->addElement('param', false, 'Empty', false, + $this->addElement( + 'param', + false, + 'Empty', + null, array( 'id' => 'ID', 'name*' => 'Text', 'type' => 'Text', 'value' => 'Text', 'valuetype' => 'Enum#data,ref,object' - ) + ) ); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Presentation.php b/library/HTMLPurifier/HTMLModule/Presentation.php index 8ff0b5ed7..6458ce9d8 100644 --- a/library/HTMLPurifier/HTMLModule/Presentation.php +++ b/library/HTMLPurifier/HTMLModule/Presentation.php @@ -13,24 +13,30 @@ class HTMLPurifier_HTMLModule_Presentation extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Presentation'; - public function setup($config) { - $this->addElement('hr', 'Block', 'Empty', 'Common'); - $this->addElement('sub', 'Inline', 'Inline', 'Common'); - $this->addElement('sup', 'Inline', 'Inline', 'Common'); - $b = $this->addElement('b', 'Inline', 'Inline', 'Common'); + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement('hr', 'Block', 'Empty', 'Common'); + $this->addElement('sub', 'Inline', 'Inline', 'Common'); + $this->addElement('sup', 'Inline', 'Inline', 'Common'); + $b = $this->addElement('b', 'Inline', 'Inline', 'Common'); $b->formatting = true; - $big = $this->addElement('big', 'Inline', 'Inline', 'Common'); + $big = $this->addElement('big', 'Inline', 'Inline', 'Common'); $big->formatting = true; - $i = $this->addElement('i', 'Inline', 'Inline', 'Common'); + $i = $this->addElement('i', 'Inline', 'Inline', 'Common'); $i->formatting = true; - $small = $this->addElement('small', 'Inline', 'Inline', 'Common'); + $small = $this->addElement('small', 'Inline', 'Inline', 'Common'); $small->formatting = true; - $tt = $this->addElement('tt', 'Inline', 'Inline', 'Common'); + $tt = $this->addElement('tt', 'Inline', 'Inline', 'Common'); $tt->formatting = true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Proprietary.php b/library/HTMLPurifier/HTMLModule/Proprietary.php index dd36a3de0..5ee3c8e67 100644 --- a/library/HTMLPurifier/HTMLModule/Proprietary.php +++ b/library/HTMLPurifier/HTMLModule/Proprietary.php @@ -6,12 +6,21 @@ */ class HTMLPurifier_HTMLModule_Proprietary extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Proprietary'; - public function setup($config) { - - $this->addElement('marquee', 'Inline', 'Flow', 'Common', + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'marquee', + 'Inline', + 'Flow', + 'Common', array( 'direction' => 'Enum#left,right,up,down', 'behavior' => 'Enum#alternate', @@ -25,9 +34,7 @@ class HTMLPurifier_HTMLModule_Proprietary extends HTMLPurifier_HTMLModule 'vspace' => 'Pixels', ) ); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Ruby.php b/library/HTMLPurifier/HTMLModule/Ruby.php index b26a0a30a..a0d48924d 100644 --- a/library/HTMLPurifier/HTMLModule/Ruby.php +++ b/library/HTMLPurifier/HTMLModule/Ruby.php @@ -7,12 +7,22 @@ class HTMLPurifier_HTMLModule_Ruby extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Ruby'; - public function setup($config) { - $this->addElement('ruby', 'Inline', + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'ruby', + 'Inline', 'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))', - 'Common'); + 'Common' + ); $this->addElement('rbc', false, 'Required: rb', 'Common'); $this->addElement('rtc', false, 'Required: rt', 'Common'); $rb = $this->addElement('rb', false, 'Inline', 'Common'); @@ -21,7 +31,6 @@ class HTMLPurifier_HTMLModule_Ruby extends HTMLPurifier_HTMLModule $rt->excludes = array('ruby' => true); $this->addElement('rp', false, 'Optional: #PCDATA', 'Common'); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/SafeEmbed.php b/library/HTMLPurifier/HTMLModule/SafeEmbed.php index ea256716b..04e6689ea 100644 --- a/library/HTMLPurifier/HTMLModule/SafeEmbed.php +++ b/library/HTMLPurifier/HTMLModule/SafeEmbed.php @@ -5,14 +5,22 @@ */ class HTMLPurifier_HTMLModule_SafeEmbed extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'SafeEmbed'; - public function setup($config) { - + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $max = $config->get('HTML.MaxImgLength'); $embed = $this->addElement( - 'embed', 'Inline', 'Empty', 'Common', + 'embed', + 'Inline', + 'Empty', + 'Common', array( 'src*' => 'URI#embedded', 'type' => 'Enum#application/x-shockwave-flash', @@ -21,14 +29,12 @@ class HTMLPurifier_HTMLModule_SafeEmbed extends HTMLPurifier_HTMLModule 'allowscriptaccess' => 'Enum#never', 'allownetworking' => 'Enum#internal', 'flashvars' => 'Text', - 'wmode' => 'Enum#window', + 'wmode' => 'Enum#window,transparent,opaque', 'name' => 'ID', ) ); $embed->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeEmbed(); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/SafeObject.php b/library/HTMLPurifier/HTMLModule/SafeObject.php index 64ab8c070..1297f80a3 100644 --- a/library/HTMLPurifier/HTMLModule/SafeObject.php +++ b/library/HTMLPurifier/HTMLModule/SafeObject.php @@ -8,11 +8,16 @@ */ class HTMLPurifier_HTMLModule_SafeObject extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'SafeObject'; - public function setup($config) { - + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { // These definitions are not intrinsically safe: the attribute transforms // are a vital part of ensuring safety. @@ -25,18 +30,24 @@ class HTMLPurifier_HTMLModule_SafeObject extends HTMLPurifier_HTMLModule array( // While technically not required by the spec, we're forcing // it to this value. - 'type' => 'Enum#application/x-shockwave-flash', - 'width' => 'Pixels#' . $max, + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, 'height' => 'Pixels#' . $max, - 'data' => 'URI#embedded', - 'classid' => 'Enum#clsid:d27cdb6e-ae6d-11cf-96b8-444553540000', - 'codebase' => new HTMLPurifier_AttrDef_Enum(array( - 'http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0')), + 'data' => 'URI#embedded', + 'codebase' => new HTMLPurifier_AttrDef_Enum( + array( + 'http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0' + ) + ), ) ); $object->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeObject(); - $param = $this->addElement('param', false, 'Empty', false, + $param = $this->addElement( + 'param', + false, + 'Empty', + false, array( 'id' => 'ID', 'name*' => 'Text', @@ -45,9 +56,7 @@ class HTMLPurifier_HTMLModule_SafeObject extends HTMLPurifier_HTMLModule ); $param->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeParam(); $this->info_injector[] = 'SafeObject'; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/SafeScripting.php b/library/HTMLPurifier/HTMLModule/SafeScripting.php new file mode 100644 index 000000000..0330cd97f --- /dev/null +++ b/library/HTMLPurifier/HTMLModule/SafeScripting.php @@ -0,0 +1,40 @@ +<?php + +/** + * A "safe" script module. No inline JS is allowed, and pointed to JS + * files must match whitelist. + */ +class HTMLPurifier_HTMLModule_SafeScripting extends HTMLPurifier_HTMLModule +{ + /** + * @type string + */ + public $name = 'SafeScripting'; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + // These definitions are not intrinsically safe: the attribute transforms + // are a vital part of ensuring safety. + + $allowed = $config->get('HTML.SafeScripting'); + $script = $this->addElement( + 'script', + 'Inline', + 'Empty', + null, + array( + // While technically not required by the spec, we're forcing + // it to this value. + 'type' => 'Enum#text/javascript', + 'src*' => new HTMLPurifier_AttrDef_Enum(array_keys($allowed)) + ) + ); + $script->attr_transform_pre[] = + $script->attr_transform_post[] = new HTMLPurifier_AttrTransform_ScriptRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Scripting.php b/library/HTMLPurifier/HTMLModule/Scripting.php index cecdea6c3..8b28a7b7e 100644 --- a/library/HTMLPurifier/HTMLModule/Scripting.php +++ b/library/HTMLPurifier/HTMLModule/Scripting.php @@ -15,12 +15,31 @@ INSIDE HTML PURIFIER DOCUMENTS. USE ONLY WITH TRUSTED USER INPUT!!! */ class HTMLPurifier_HTMLModule_Scripting extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'Scripting'; + + /** + * @type array + */ public $elements = array('script', 'noscript'); + + /** + * @type array + */ public $content_sets = array('Block' => 'script | noscript', 'Inline' => 'script | noscript'); + + /** + * @type bool + */ public $safe = false; - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { // TODO: create custom child-definition for noscript that // auto-wraps stray #PCDATA in a similar manner to // blockquote's custom definition (we would use it but @@ -33,20 +52,20 @@ class HTMLPurifier_HTMLModule_Scripting extends HTMLPurifier_HTMLModule // In theory, this could be safe, but I don't see any reason to // allow it. $this->info['noscript'] = new HTMLPurifier_ElementDef(); - $this->info['noscript']->attr = array( 0 => array('Common') ); + $this->info['noscript']->attr = array(0 => array('Common')); $this->info['noscript']->content_model = 'Heading | List | Block'; $this->info['noscript']->content_model_type = 'required'; $this->info['script'] = new HTMLPurifier_ElementDef(); $this->info['script']->attr = array( 'defer' => new HTMLPurifier_AttrDef_Enum(array('defer')), - 'src' => new HTMLPurifier_AttrDef_URI(true), - 'type' => new HTMLPurifier_AttrDef_Enum(array('text/javascript')) + 'src' => new HTMLPurifier_AttrDef_URI(true), + 'type' => new HTMLPurifier_AttrDef_Enum(array('text/javascript')) ); $this->info['script']->content_model = '#PCDATA'; $this->info['script']->content_model_type = 'optional'; - $this->info['script']->attr_transform_pre['type'] = - $this->info['script']->attr_transform_post['type'] = + $this->info['script']->attr_transform_pre[] = + $this->info['script']->attr_transform_post[] = new HTMLPurifier_AttrTransform_ScriptRequired(); } } diff --git a/library/HTMLPurifier/HTMLModule/StyleAttribute.php b/library/HTMLPurifier/HTMLModule/StyleAttribute.php index eb78464cc..497b832ae 100644 --- a/library/HTMLPurifier/HTMLModule/StyleAttribute.php +++ b/library/HTMLPurifier/HTMLModule/StyleAttribute.php @@ -6,8 +6,14 @@ */ class HTMLPurifier_HTMLModule_StyleAttribute extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'StyleAttribute'; + + /** + * @type array + */ public $attr_collections = array( // The inclusion routine differs from the Abstract Modules but // is in line with the DTD and XML Schemas. @@ -15,10 +21,13 @@ class HTMLPurifier_HTMLModule_StyleAttribute extends HTMLPurifier_HTMLModule 'Core' => array(0 => array('Style')) ); - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $this->attr_collections['Style']['style'] = new HTMLPurifier_AttrDef_CSS(); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Tables.php b/library/HTMLPurifier/HTMLModule/Tables.php index f314ced3f..8a0b3b461 100644 --- a/library/HTMLPurifier/HTMLModule/Tables.php +++ b/library/HTMLPurifier/HTMLModule/Tables.php @@ -5,15 +5,23 @@ */ class HTMLPurifier_HTMLModule_Tables extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Tables'; - public function setup($config) { - + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $this->addElement('caption', false, 'Inline', 'Common'); - $this->addElement('table', 'Block', - new HTMLPurifier_ChildDef_Table(), 'Common', + $this->addElement( + 'table', + 'Block', + new HTMLPurifier_ChildDef_Table(), + 'Common', array( 'border' => 'Pixels', 'cellpadding' => 'Length', @@ -34,9 +42,12 @@ class HTMLPurifier_HTMLModule_Tables extends HTMLPurifier_HTMLModule $cell_t = array_merge( array( - 'abbr' => 'Text', + 'abbr' => 'Text', 'colspan' => 'Number', 'rowspan' => 'Number', + // Apparently, as of HTML5 this attribute only applies + // to 'th' elements. + 'scope' => 'Enum#row,col,rowgroup,colgroup', ), $cell_align ); @@ -47,20 +58,18 @@ class HTMLPurifier_HTMLModule_Tables extends HTMLPurifier_HTMLModule $cell_col = array_merge( array( - 'span' => 'Number', + 'span' => 'Number', 'width' => 'MultiLength', ), $cell_align ); - $this->addElement('col', false, 'Empty', 'Common', $cell_col); + $this->addElement('col', false, 'Empty', 'Common', $cell_col); $this->addElement('colgroup', false, 'Optional: col', 'Common', $cell_col); $this->addElement('tbody', false, 'Required: tr', 'Common', $cell_align); $this->addElement('thead', false, 'Required: tr', 'Common', $cell_align); $this->addElement('tfoot', false, 'Required: tr', 'Common', $cell_align); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Target.php b/library/HTMLPurifier/HTMLModule/Target.php index 2b844ecc4..b188ac936 100644 --- a/library/HTMLPurifier/HTMLModule/Target.php +++ b/library/HTMLPurifier/HTMLModule/Target.php @@ -5,10 +5,16 @@ */ class HTMLPurifier_HTMLModule_Target extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Target'; - public function setup($config) { + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { $elements = array('a'); foreach ($elements as $name) { $e = $this->addBlankElement($name); @@ -17,7 +23,6 @@ class HTMLPurifier_HTMLModule_Target extends HTMLPurifier_HTMLModule ); } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/TargetBlank.php b/library/HTMLPurifier/HTMLModule/TargetBlank.php new file mode 100644 index 000000000..58ccc6894 --- /dev/null +++ b/library/HTMLPurifier/HTMLModule/TargetBlank.php @@ -0,0 +1,24 @@ +<?php + +/** + * Module adds the target=blank attribute transformation to a tags. It + * is enabled by HTML.TargetBlank + */ +class HTMLPurifier_HTMLModule_TargetBlank extends HTMLPurifier_HTMLModule +{ + /** + * @type string + */ + public $name = 'TargetBlank'; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $a = $this->addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_TargetBlank(); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Text.php b/library/HTMLPurifier/HTMLModule/Text.php index ae77c7188..7a65e0048 100644 --- a/library/HTMLPurifier/HTMLModule/Text.php +++ b/library/HTMLPurifier/HTMLModule/Text.php @@ -14,43 +14,59 @@ */ class HTMLPurifier_HTMLModule_Text extends HTMLPurifier_HTMLModule { - + /** + * @type string + */ public $name = 'Text'; + + /** + * @type array + */ public $content_sets = array( 'Flow' => 'Heading | Block | Inline' ); - public function setup($config) { - + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { // Inline Phrasal ------------------------------------------------- - $this->addElement('abbr', 'Inline', 'Inline', 'Common'); + $this->addElement('abbr', 'Inline', 'Inline', 'Common'); $this->addElement('acronym', 'Inline', 'Inline', 'Common'); - $this->addElement('cite', 'Inline', 'Inline', 'Common'); - $this->addElement('dfn', 'Inline', 'Inline', 'Common'); - $this->addElement('kbd', 'Inline', 'Inline', 'Common'); - $this->addElement('q', 'Inline', 'Inline', 'Common', array('cite' => 'URI')); - $this->addElement('samp', 'Inline', 'Inline', 'Common'); - $this->addElement('var', 'Inline', 'Inline', 'Common'); + $this->addElement('cite', 'Inline', 'Inline', 'Common'); + $this->addElement('dfn', 'Inline', 'Inline', 'Common'); + $this->addElement('kbd', 'Inline', 'Inline', 'Common'); + $this->addElement('q', 'Inline', 'Inline', 'Common', array('cite' => 'URI')); + $this->addElement('samp', 'Inline', 'Inline', 'Common'); + $this->addElement('var', 'Inline', 'Inline', 'Common'); - $em = $this->addElement('em', 'Inline', 'Inline', 'Common'); + $em = $this->addElement('em', 'Inline', 'Inline', 'Common'); $em->formatting = true; - $strong = $this->addElement('strong', 'Inline', 'Inline', 'Common'); + $strong = $this->addElement('strong', 'Inline', 'Inline', 'Common'); $strong->formatting = true; - $code = $this->addElement('code', 'Inline', 'Inline', 'Common'); + $code = $this->addElement('code', 'Inline', 'Inline', 'Common'); $code->formatting = true; // Inline Structural ---------------------------------------------- $this->addElement('span', 'Inline', 'Inline', 'Common'); - $this->addElement('br', 'Inline', 'Empty', 'Core'); + $this->addElement('br', 'Inline', 'Empty', 'Core'); // Block Phrasal -------------------------------------------------- - $this->addElement('address', 'Block', 'Inline', 'Common'); - $this->addElement('blockquote', 'Block', 'Optional: Heading | Block | List', 'Common', array('cite' => 'URI') ); + $this->addElement('address', 'Block', 'Inline', 'Common'); + $this->addElement('blockquote', 'Block', 'Optional: Heading | Block | List', 'Common', array('cite' => 'URI')); $pre = $this->addElement('pre', 'Block', 'Inline', 'Common'); $pre->excludes = $this->makeLookup( - 'img', 'big', 'small', 'object', 'applet', 'font', 'basefont' ); + 'img', + 'big', + 'small', + 'object', + 'applet', + 'font', + 'basefont' + ); $this->addElement('h1', 'Heading', 'Inline', 'Common'); $this->addElement('h2', 'Heading', 'Inline', 'Common'); $this->addElement('h3', 'Heading', 'Inline', 'Common'); @@ -60,12 +76,12 @@ class HTMLPurifier_HTMLModule_Text extends HTMLPurifier_HTMLModule // Block Structural ----------------------------------------------- $p = $this->addElement('p', 'Block', 'Inline', 'Common'); - $p->autoclose = array_flip(array("address", "blockquote", "center", "dir", "div", "dl", "fieldset", "ol", "p", "ul")); + $p->autoclose = array_flip( + array("address", "blockquote", "center", "dir", "div", "dl", "fieldset", "ol", "p", "ul") + ); $this->addElement('div', 'Block', 'Flow', 'Common'); - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Tidy.php b/library/HTMLPurifier/HTMLModule/Tidy.php index 21783f18e..08aa23247 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy.php +++ b/library/HTMLPurifier/HTMLModule/Tidy.php @@ -7,36 +7,41 @@ */ class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule { - /** - * List of supported levels. Index zero is a special case "no fixes" - * level. + * List of supported levels. + * Index zero is a special case "no fixes" level. + * @type array */ public $levels = array(0 => 'none', 'light', 'medium', 'heavy'); /** - * Default level to place all fixes in. Disabled by default + * Default level to place all fixes in. + * Disabled by default. + * @type string */ public $defaultLevel = null; /** - * Lists of fixes used by getFixesForLevel(). Format is: + * Lists of fixes used by getFixesForLevel(). + * Format is: * HTMLModule_Tidy->fixesForLevel[$level] = array('fix-1', 'fix-2'); + * @type array */ public $fixesForLevel = array( - 'light' => array(), + 'light' => array(), 'medium' => array(), - 'heavy' => array() + 'heavy' => array() ); /** * Lazy load constructs the module by determining the necessary * fixes to create and then delegating to the populate() function. + * @param HTMLPurifier_Config $config * @todo Wildcard matching and error reporting when an added or * subtracted fix has no effect. */ - public function setup($config) { - + public function setup($config) + { // create fixes, initialize fixesForLevel $fixes = $this->makeFixes(); $this->makeFixesForLevel($fixes); @@ -46,38 +51,38 @@ class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule $fixes_lookup = $this->getFixesForLevel($level); // get custom fix declarations: these need namespace processing - $add_fixes = $config->get('HTML.TidyAdd'); + $add_fixes = $config->get('HTML.TidyAdd'); $remove_fixes = $config->get('HTML.TidyRemove'); foreach ($fixes as $name => $fix) { // needs to be refactored a little to implement globbing - if ( - isset($remove_fixes[$name]) || - (!isset($add_fixes[$name]) && !isset($fixes_lookup[$name])) - ) { + if (isset($remove_fixes[$name]) || + (!isset($add_fixes[$name]) && !isset($fixes_lookup[$name]))) { unset($fixes[$name]); } } // populate this module with necessary fixes $this->populate($fixes); - } /** * Retrieves all fixes per a level, returning fixes for that specific * level as well as all levels below it. - * @param $level String level identifier, see $levels for valid values - * @return Lookup up table of fixes + * @param string $level level identifier, see $levels for valid values + * @return array Lookup up table of fixes */ - public function getFixesForLevel($level) { + public function getFixesForLevel($level) + { if ($level == $this->levels[0]) { return array(); } $activated_levels = array(); for ($i = 1, $c = count($this->levels); $i < $c; $i++) { $activated_levels[] = $this->levels[$i]; - if ($this->levels[$i] == $level) break; + if ($this->levels[$i] == $level) { + break; + } } if ($i == $c) { trigger_error( @@ -99,9 +104,13 @@ class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule * Dynamically populates the $fixesForLevel member variable using * the fixes array. It may be custom overloaded, used in conjunction * with $defaultLevel, or not used at all. + * @param array $fixes */ - public function makeFixesForLevel($fixes) { - if (!isset($this->defaultLevel)) return; + public function makeFixesForLevel($fixes) + { + if (!isset($this->defaultLevel)) { + return; + } if (!isset($this->fixesForLevel[$this->defaultLevel])) { trigger_error( 'Default level ' . $this->defaultLevel . ' does not exist', @@ -115,9 +124,10 @@ class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule /** * Populates the module with transforms and other special-case code * based on a list of fixes passed to it - * @param $lookup Lookup table of fixes to activate + * @param array $fixes Lookup table of fixes to activate */ - public function populate($fixes) { + public function populate($fixes) + { foreach ($fixes as $name => $fix) { // determine what the fix is for list($type, $params) = $this->getFixType($name); @@ -169,20 +179,31 @@ class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule * @note $fix_parameters is type dependant, see populate() for usage * of these parameters */ - public function getFixType($name) { + public function getFixType($name) + { // parse it $property = $attr = null; - if (strpos($name, '#') !== false) list($name, $property) = explode('#', $name); - if (strpos($name, '@') !== false) list($name, $attr) = explode('@', $name); + if (strpos($name, '#') !== false) { + list($name, $property) = explode('#', $name); + } + if (strpos($name, '@') !== false) { + list($name, $attr) = explode('@', $name); + } // figure out the parameters $params = array(); - if ($name !== '') $params['element'] = $name; - if (!is_null($attr)) $params['attr'] = $attr; + if ($name !== '') { + $params['element'] = $name; + } + if (!is_null($attr)) { + $params['attr'] = $attr; + } // special case: attribute transform if (!is_null($attr)) { - if (is_null($property)) $property = 'pre'; + if (is_null($property)) { + $property = 'pre'; + } $type = 'attr_transform_' . $property; return array($type, $params); } @@ -199,9 +220,11 @@ class HTMLPurifier_HTMLModule_Tidy extends HTMLPurifier_HTMLModule /** * Defines all fixes the module will perform in a compact * associative array of fix name to fix implementation. + * @return array */ - public function makeFixes() {} - + public function makeFixes() + { + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Tidy/Name.php b/library/HTMLPurifier/HTMLModule/Tidy/Name.php index 61ff85ce2..a995161b2 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy/Name.php +++ b/library/HTMLPurifier/HTMLModule/Tidy/Name.php @@ -5,18 +5,27 @@ */ class HTMLPurifier_HTMLModule_Tidy_Name extends HTMLPurifier_HTMLModule_Tidy { + /** + * @type string + */ public $name = 'Tidy_Name'; + + /** + * @type string + */ public $defaultLevel = 'heavy'; - public function makeFixes() { + /** + * @return array + */ + public function makeFixes() + { $r = array(); - // @name for img, a ----------------------------------------------- // Technically, it's allowed even on strict, so we allow authors to use // it. However, it's deprecated in future versions of XHTML. $r['img@name'] = $r['a@name'] = new HTMLPurifier_AttrTransform_Name(); - return $r; } } diff --git a/library/HTMLPurifier/HTMLModule/Tidy/Proprietary.php b/library/HTMLPurifier/HTMLModule/Tidy/Proprietary.php index 14c15c4a0..332643821 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy/Proprietary.php +++ b/library/HTMLPurifier/HTMLModule/Tidy/Proprietary.php @@ -3,10 +3,21 @@ class HTMLPurifier_HTMLModule_Tidy_Proprietary extends HTMLPurifier_HTMLModule_Tidy { + /** + * @type string + */ public $name = 'Tidy_Proprietary'; + + /** + * @type string + */ public $defaultLevel = 'light'; - public function makeFixes() { + /** + * @return array + */ + public function makeFixes() + { $r = array(); $r['table@background'] = new HTMLPurifier_AttrTransform_Background(); $r['td@background'] = new HTMLPurifier_AttrTransform_Background(); @@ -18,7 +29,6 @@ class HTMLPurifier_HTMLModule_Tidy_Proprietary extends HTMLPurifier_HTMLModule_T $r['table@height'] = new HTMLPurifier_AttrTransform_Length('height'); return $r; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Tidy/Strict.php b/library/HTMLPurifier/HTMLModule/Tidy/Strict.php index c73dc3c4d..803c44fab 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy/Strict.php +++ b/library/HTMLPurifier/HTMLModule/Tidy/Strict.php @@ -2,18 +2,40 @@ class HTMLPurifier_HTMLModule_Tidy_Strict extends HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 { + /** + * @type string + */ public $name = 'Tidy_Strict'; + + /** + * @type string + */ public $defaultLevel = 'light'; - public function makeFixes() { + /** + * @return array + */ + public function makeFixes() + { $r = parent::makeFixes(); $r['blockquote#content_model_type'] = 'strictblockquote'; return $r; } + /** + * @type bool + */ public $defines_child_def = true; - public function getChildDef($def) { - if ($def->content_model_type != 'strictblockquote') return parent::getChildDef($def); + + /** + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef_StrictBlockquote + */ + public function getChildDef($def) + { + if ($def->content_model_type != 'strictblockquote') { + return parent::getChildDef($def); + } return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model); } } diff --git a/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php b/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php index 9960b1dd1..c095ad974 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php +++ b/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php @@ -2,7 +2,14 @@ class HTMLPurifier_HTMLModule_Tidy_Transitional extends HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 { + /** + * @type string + */ public $name = 'Tidy_Transitional'; + + /** + * @type string + */ public $defaultLevel = 'heavy'; } diff --git a/library/HTMLPurifier/HTMLModule/Tidy/XHTML.php b/library/HTMLPurifier/HTMLModule/Tidy/XHTML.php index db5a378e5..3ecddc434 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy/XHTML.php +++ b/library/HTMLPurifier/HTMLModule/Tidy/XHTML.php @@ -2,16 +2,25 @@ class HTMLPurifier_HTMLModule_Tidy_XHTML extends HTMLPurifier_HTMLModule_Tidy { - + /** + * @type string + */ public $name = 'Tidy_XHTML'; + + /** + * @type string + */ public $defaultLevel = 'medium'; - public function makeFixes() { + /** + * @return array + */ + public function makeFixes() + { $r = array(); $r['@lang'] = new HTMLPurifier_AttrTransform_Lang(); return $r; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php b/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php index 02e943813..c4f16a4dc 100644 --- a/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php +++ b/library/HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php @@ -3,69 +3,86 @@ class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends HTMLPurifier_HTMLModule_Tidy { - public function makeFixes() { - + /** + * @return array + */ + public function makeFixes() + { $r = array(); // == deprecated tag transforms =================================== - $r['font'] = new HTMLPurifier_TagTransform_Font(); - $r['menu'] = new HTMLPurifier_TagTransform_Simple('ul'); - $r['dir'] = new HTMLPurifier_TagTransform_Simple('ul'); - $r['center'] = new HTMLPurifier_TagTransform_Simple('div', 'text-align:center;'); - $r['u'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:underline;'); - $r['s'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:line-through;'); + $r['font'] = new HTMLPurifier_TagTransform_Font(); + $r['menu'] = new HTMLPurifier_TagTransform_Simple('ul'); + $r['dir'] = new HTMLPurifier_TagTransform_Simple('ul'); + $r['center'] = new HTMLPurifier_TagTransform_Simple('div', 'text-align:center;'); + $r['u'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:underline;'); + $r['s'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:line-through;'); $r['strike'] = new HTMLPurifier_TagTransform_Simple('span', 'text-decoration:line-through;'); // == deprecated attribute transforms ============================= $r['caption@align'] = - new HTMLPurifier_AttrTransform_EnumToCSS('align', array( - // we're following IE's behavior, not Firefox's, due - // to the fact that no one supports caption-side:right, - // W3C included (with CSS 2.1). This is a slightly - // unreasonable attribute! - 'left' => 'text-align:left;', - 'right' => 'text-align:right;', - 'top' => 'caption-side:top;', - 'bottom' => 'caption-side:bottom;' // not supported by IE - )); + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + // we're following IE's behavior, not Firefox's, due + // to the fact that no one supports caption-side:right, + // W3C included (with CSS 2.1). This is a slightly + // unreasonable attribute! + 'left' => 'text-align:left;', + 'right' => 'text-align:right;', + 'top' => 'caption-side:top;', + 'bottom' => 'caption-side:bottom;' // not supported by IE + ) + ); // @align for img ------------------------------------------------- $r['img@align'] = - new HTMLPurifier_AttrTransform_EnumToCSS('align', array( - 'left' => 'float:left;', - 'right' => 'float:right;', - 'top' => 'vertical-align:top;', - 'middle' => 'vertical-align:middle;', - 'bottom' => 'vertical-align:baseline;', - )); + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + 'left' => 'float:left;', + 'right' => 'float:right;', + 'top' => 'vertical-align:top;', + 'middle' => 'vertical-align:middle;', + 'bottom' => 'vertical-align:baseline;', + ) + ); // @align for table ----------------------------------------------- $r['table@align'] = - new HTMLPurifier_AttrTransform_EnumToCSS('align', array( - 'left' => 'float:left;', - 'center' => 'margin-left:auto;margin-right:auto;', - 'right' => 'float:right;' - )); + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + 'left' => 'float:left;', + 'center' => 'margin-left:auto;margin-right:auto;', + 'right' => 'float:right;' + ) + ); // @align for hr ----------------------------------------------- $r['hr@align'] = - new HTMLPurifier_AttrTransform_EnumToCSS('align', array( - // we use both text-align and margin because these work - // for different browsers (IE and Firefox, respectively) - // and the melange makes for a pretty cross-compatible - // solution - 'left' => 'margin-left:0;margin-right:auto;text-align:left;', - 'center' => 'margin-left:auto;margin-right:auto;text-align:center;', - 'right' => 'margin-left:auto;margin-right:0;text-align:right;' - )); + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + // we use both text-align and margin because these work + // for different browsers (IE and Firefox, respectively) + // and the melange makes for a pretty cross-compatible + // solution + 'left' => 'margin-left:0;margin-right:auto;text-align:left;', + 'center' => 'margin-left:auto;margin-right:auto;text-align:center;', + 'right' => 'margin-left:auto;margin-right:0;text-align:right;' + ) + ); // @align for h1, h2, h3, h4, h5, h6, p, div ---------------------- // {{{ - $align_lookup = array(); - $align_values = array('left', 'right', 'center', 'justify'); - foreach ($align_values as $v) $align_lookup[$v] = "text-align:$v;"; + $align_lookup = array(); + $align_values = array('left', 'right', 'center', 'justify'); + foreach ($align_values as $v) { + $align_lookup[$v] = "text-align:$v;"; + } // }}} $r['h1@align'] = $r['h2@align'] = @@ -73,7 +90,7 @@ class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends HTMLPurifier_HTMLModule $r['h4@align'] = $r['h5@align'] = $r['h6@align'] = - $r['p@align'] = + $r['p@align'] = $r['div@align'] = new HTMLPurifier_AttrTransform_EnumToCSS('align', $align_lookup); @@ -88,12 +105,15 @@ class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends HTMLPurifier_HTMLModule // @clear for br -------------------------------------------------- $r['br@clear'] = - new HTMLPurifier_AttrTransform_EnumToCSS('clear', array( - 'left' => 'clear:left;', - 'right' => 'clear:right;', - 'all' => 'clear:both;', - 'none' => 'clear:none;', - )); + new HTMLPurifier_AttrTransform_EnumToCSS( + 'clear', + array( + 'left' => 'clear:left;', + 'right' => 'clear:right;', + 'all' => 'clear:both;', + 'none' => 'clear:none;', + ) + ); // @height for td, th --------------------------------------------- $r['td@height'] = @@ -125,19 +145,19 @@ class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends HTMLPurifier_HTMLModule // @type for li, ol, ul ------------------------------------------- // {{{ - $ul_types = array( - 'disc' => 'list-style-type:disc;', - 'square' => 'list-style-type:square;', - 'circle' => 'list-style-type:circle;' - ); - $ol_types = array( - '1' => 'list-style-type:decimal;', - 'i' => 'list-style-type:lower-roman;', - 'I' => 'list-style-type:upper-roman;', - 'a' => 'list-style-type:lower-alpha;', - 'A' => 'list-style-type:upper-alpha;' - ); - $li_types = $ul_types + $ol_types; + $ul_types = array( + 'disc' => 'list-style-type:disc;', + 'square' => 'list-style-type:square;', + 'circle' => 'list-style-type:circle;' + ); + $ol_types = array( + '1' => 'list-style-type:decimal;', + 'i' => 'list-style-type:lower-roman;', + 'I' => 'list-style-type:upper-roman;', + 'a' => 'list-style-type:lower-alpha;', + 'A' => 'list-style-type:upper-alpha;' + ); + $li_types = $ul_types + $ol_types; // }}} $r['ul@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ul_types); @@ -153,9 +173,7 @@ class HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4 extends HTMLPurifier_HTMLModule $r['hr@width'] = new HTMLPurifier_AttrTransform_Length('width'); return $r; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php b/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php index 9c0e03198..01dbe9deb 100644 --- a/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php +++ b/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php @@ -2,8 +2,14 @@ class HTMLPurifier_HTMLModule_XMLCommonAttributes extends HTMLPurifier_HTMLModule { + /** + * @type string + */ public $name = 'XMLCommonAttributes'; + /** + * @type array + */ public $attr_collections = array( 'Lang' => array( 'xml:lang' => 'LanguageCode', diff --git a/library/HTMLPurifier/HTMLModuleManager.php b/library/HTMLPurifier/HTMLModuleManager.php index f5c4a1d2c..f3a17cb03 100644 --- a/library/HTMLPurifier/HTMLModuleManager.php +++ b/library/HTMLPurifier/HTMLModuleManager.php @@ -4,57 +4,75 @@ class HTMLPurifier_HTMLModuleManager { /** - * Instance of HTMLPurifier_DoctypeRegistry + * @type HTMLPurifier_DoctypeRegistry */ public $doctypes; /** - * Instance of current doctype + * Instance of current doctype. + * @type string */ public $doctype; /** - * Instance of HTMLPurifier_AttrTypes + * @type HTMLPurifier_AttrTypes */ public $attrTypes; /** * Active instances of modules for the specified doctype are * indexed, by name, in this array. + * @type HTMLPurifier_HTMLModule[] */ public $modules = array(); /** - * Array of recognized HTMLPurifier_Module instances, indexed by - * module's class name. This array is usually lazy loaded, but a + * Array of recognized HTMLPurifier_HTMLModule instances, + * indexed by module's class name. This array is usually lazy loaded, but a * user can overload a module by pre-emptively registering it. + * @type HTMLPurifier_HTMLModule[] */ public $registeredModules = array(); /** - * List of extra modules that were added by the user using addModule(). - * These get unconditionally merged into the current doctype, whatever + * List of extra modules that were added by the user + * using addModule(). These get unconditionally merged into the current doctype, whatever * it may be. + * @type HTMLPurifier_HTMLModule[] */ public $userModules = array(); /** * Associative array of element name to list of modules that have * definitions for the element; this array is dynamically filled. + * @type array */ public $elementLookup = array(); - /** List of prefixes we should use for registering small names */ + /** + * List of prefixes we should use for registering small names. + * @type array + */ public $prefixes = array('HTMLPurifier_HTMLModule_'); - public $contentSets; /**< Instance of HTMLPurifier_ContentSets */ - public $attrCollections; /**< Instance of HTMLPurifier_AttrCollections */ + /** + * @type HTMLPurifier_ContentSets + */ + public $contentSets; - /** If set to true, unsafe elements and attributes will be allowed */ - public $trusted = false; + /** + * @type HTMLPurifier_AttrCollections + */ + public $attrCollections; - public function __construct() { + /** + * If set to true, unsafe elements and attributes will be allowed. + * @type bool + */ + public $trusted = false; + public function __construct() + { // editable internal objects $this->attrTypes = new HTMLPurifier_AttrTypes(); $this->doctypes = new HTMLPurifier_DoctypeRegistry(); @@ -65,17 +83,18 @@ class HTMLPurifier_HTMLModuleManager 'Presentation', 'Edit', 'Bdo', 'Tables', 'Image', 'StyleAttribute', // Unsafe: - 'Scripting', 'Object', 'Forms', + 'Scripting', 'Object', 'Forms', // Sorta legacy, but present in strict: 'Name', ); - $transitional = array('Legacy', 'Target'); + $transitional = array('Legacy', 'Target', 'Iframe'); $xml = array('XMLCommonAttributes'); $non_xml = array('NonXMLCommonAttributes'); // setup basic doctypes $this->doctypes->register( - 'HTML 4.01 Transitional', false, + 'HTML 4.01 Transitional', + false, array_merge($common, $transitional, $non_xml), array('Tidy_Transitional', 'Tidy_Proprietary'), array(), @@ -84,7 +103,8 @@ class HTMLPurifier_HTMLModuleManager ); $this->doctypes->register( - 'HTML 4.01 Strict', false, + 'HTML 4.01 Strict', + false, array_merge($common, $non_xml), array('Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'), array(), @@ -93,7 +113,8 @@ class HTMLPurifier_HTMLModuleManager ); $this->doctypes->register( - 'XHTML 1.0 Transitional', true, + 'XHTML 1.0 Transitional', + true, array_merge($common, $transitional, $xml, $non_xml), array('Tidy_Transitional', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Name'), array(), @@ -102,7 +123,8 @@ class HTMLPurifier_HTMLModuleManager ); $this->doctypes->register( - 'XHTML 1.0 Strict', true, + 'XHTML 1.0 Strict', + true, array_merge($common, $xml, $non_xml), array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'), array(), @@ -111,8 +133,11 @@ class HTMLPurifier_HTMLModuleManager ); $this->doctypes->register( - 'XHTML 1.1', true, - array_merge($common, $xml, array('Ruby')), + 'XHTML 1.1', + true, + // Iframe is a real XHTML 1.1 module, despite being + // "transitional"! + array_merge($common, $xml, array('Ruby', 'Iframe')), array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Strict', 'Tidy_Name'), // Tidy_XHTML1_1 array(), '-//W3C//DTD XHTML 1.1//EN', @@ -142,7 +167,8 @@ class HTMLPurifier_HTMLModuleManager * your module manually. All modules must have been included * externally: registerModule will not perform inclusions for you! */ - public function registerModule($module, $overload = false) { + public function registerModule($module, $overload = false) + { if (is_string($module)) { // attempt to load the module $original_module = $module; @@ -157,8 +183,10 @@ class HTMLPurifier_HTMLModuleManager if (!$ok) { $module = $original_module; if (!class_exists($module)) { - trigger_error($original_module . ' module does not exist', - E_USER_ERROR); + trigger_error( + $original_module . ' module does not exist', + E_USER_ERROR + ); return; } } @@ -178,9 +206,12 @@ class HTMLPurifier_HTMLModuleManager * Adds a module to the current doctype by first registering it, * and then tacking it on to the active doctype */ - public function addModule($module) { + public function addModule($module) + { $this->registerModule($module); - if (is_object($module)) $module = $module->name; + if (is_object($module)) { + $module = $module->name; + } $this->userModules[] = $module; } @@ -188,17 +219,18 @@ class HTMLPurifier_HTMLModuleManager * Adds a class prefix that registerModule() will use to resolve a * string name to a concrete class */ - public function addPrefix($prefix) { + public function addPrefix($prefix) + { $this->prefixes[] = $prefix; } /** * Performs processing on modules, after being called you may * use getElement() and getElements() - * @param $config Instance of HTMLPurifier_Config + * @param HTMLPurifier_Config $config */ - public function setup($config) { - + public function setup($config) + { $this->trusted = $config->get('HTML.Trusted'); // generate @@ -211,24 +243,34 @@ class HTMLPurifier_HTMLModuleManager if (is_array($lookup)) { foreach ($modules as $k => $m) { - if (isset($special_cases[$m])) continue; - if (!isset($lookup[$m])) unset($modules[$k]); + if (isset($special_cases[$m])) { + continue; + } + if (!isset($lookup[$m])) { + unset($modules[$k]); + } } } - // add proprietary module (this gets special treatment because - // it is completely removed from doctypes, etc.) + // custom modules if ($config->get('HTML.Proprietary')) { $modules[] = 'Proprietary'; } - - // add SafeObject/Safeembed modules if ($config->get('HTML.SafeObject')) { $modules[] = 'SafeObject'; } if ($config->get('HTML.SafeEmbed')) { $modules[] = 'SafeEmbed'; } + if ($config->get('HTML.SafeScripting') !== array()) { + $modules[] = 'SafeScripting'; + } + if ($config->get('HTML.Nofollow')) { + $modules[] = 'Nofollow'; + } + if ($config->get('HTML.TargetBlank')) { + $modules[] = 'TargetBlank'; + } // merge in custom modules $modules = array_merge($modules, $this->userModules); @@ -246,7 +288,7 @@ class HTMLPurifier_HTMLModuleManager // prepare any injectors foreach ($this->modules as $module) { $n = array(); - foreach ($module->info_injector as $i => $injector) { + foreach ($module->info_injector as $injector) { if (!is_object($injector)) { $class = "HTMLPurifier_Injector_$injector"; $injector = new $class; @@ -285,7 +327,8 @@ class HTMLPurifier_HTMLModuleManager * Takes a module and adds it to the active module collection, * registering it if necessary. */ - public function processModule($module) { + public function processModule($module) + { if (!isset($this->registeredModules[$module]) || is_object($module)) { $this->registerModule($module); } @@ -296,13 +339,17 @@ class HTMLPurifier_HTMLModuleManager * Retrieves merged element definitions. * @return Array of HTMLPurifier_ElementDef */ - public function getElements() { - + public function getElements() + { $elements = array(); foreach ($this->modules as $module) { - if (!$this->trusted && !$module->safe) continue; + if (!$this->trusted && !$module->safe) { + continue; + } foreach ($module->info as $name => $v) { - if (isset($elements[$name])) continue; + if (isset($elements[$name])) { + continue; + } $elements[$name] = $this->getElement($name); } } @@ -310,7 +357,9 @@ class HTMLPurifier_HTMLModuleManager // remove dud elements, this happens when an element that // appeared to be safe actually wasn't foreach ($elements as $n => $v) { - if ($v === false) unset($elements[$n]); + if ($v === false) { + unset($elements[$n]); + } } return $elements; @@ -319,28 +368,29 @@ class HTMLPurifier_HTMLModuleManager /** * Retrieves a single merged element definition - * @param $name Name of element - * @param $trusted Boolean trusted overriding parameter: set to true + * @param string $name Name of element + * @param bool $trusted Boolean trusted overriding parameter: set to true * if you want the full version of an element - * @return Merged HTMLPurifier_ElementDef + * @return HTMLPurifier_ElementDef Merged HTMLPurifier_ElementDef * @note You may notice that modules are getting iterated over twice (once * in getElements() and once here). This * is because */ - public function getElement($name, $trusted = null) { - + public function getElement($name, $trusted = null) + { if (!isset($this->elementLookup[$name])) { return false; } // setup global state variables $def = false; - if ($trusted === null) $trusted = $this->trusted; + if ($trusted === null) { + $trusted = $this->trusted; + } // iterate through each module that has registered itself to this // element - foreach($this->elementLookup[$name] as $module_name) { - + foreach ($this->elementLookup[$name] as $module_name) { $module = $this->modules[$module_name]; // refuse to create/merge from a module that is deemed unsafe-- @@ -364,6 +414,13 @@ class HTMLPurifier_HTMLModuleManager // :TODO: // non-standalone definitions that don't have a standalone // to merge into could be deferred to the end + // HOWEVER, it is perfectly valid for a non-standalone + // definition to lack a standalone definition, even + // after all processing: this allows us to safely + // specify extra attributes for elements that may not be + // enabled all in one place. In particular, this might + // be the case for trusted elements. WARNING: care must + // be taken that the /extra/ definitions are all safe. continue; } @@ -385,7 +442,9 @@ class HTMLPurifier_HTMLModuleManager // This can occur if there is a blank definition, but no base to // mix it in with - if (!$def) return false; + if (!$def) { + return false; + } // add information on required attributes foreach ($def->attr as $attr_name => $attr_def) { @@ -393,11 +452,8 @@ class HTMLPurifier_HTMLModuleManager $def->required_attr[] = $attr_name; } } - return $def; - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/IDAccumulator.php b/library/HTMLPurifier/IDAccumulator.php index 73215295a..65c902c07 100644 --- a/library/HTMLPurifier/IDAccumulator.php +++ b/library/HTMLPurifier/IDAccumulator.php @@ -17,11 +17,12 @@ class HTMLPurifier_IDAccumulator /** * Builds an IDAccumulator, also initializing the default blacklist - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @return Fully initialized HTMLPurifier_IDAccumulator + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config + * @param HTMLPurifier_Context $context Instance of HTMLPurifier_Context + * @return HTMLPurifier_IDAccumulator Fully initialized HTMLPurifier_IDAccumulator */ - public static function build($config, $context) { + public static function build($config, $context) + { $id_accumulator = new HTMLPurifier_IDAccumulator(); $id_accumulator->load($config->get('Attr.IDBlacklist')); return $id_accumulator; @@ -29,11 +30,14 @@ class HTMLPurifier_IDAccumulator /** * Add an ID to the lookup table. - * @param $id ID to be added. - * @return Bool status, true if success, false if there's a dupe + * @param string $id ID to be added. + * @return bool status, true if success, false if there's a dupe */ - public function add($id) { - if (isset($this->ids[$id])) return false; + public function add($id) + { + if (isset($this->ids[$id])) { + return false; + } return $this->ids[$id] = true; } @@ -42,12 +46,12 @@ class HTMLPurifier_IDAccumulator * @param $array_of_ids Array of IDs to load * @note This function doesn't care about duplicates */ - public function load($array_of_ids) { + public function load($array_of_ids) + { foreach ($array_of_ids as $id) { $this->ids[$id] = true; } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Injector.php b/library/HTMLPurifier/Injector.php index 5922f8130..5060eef9e 100644 --- a/library/HTMLPurifier/Injector.php +++ b/library/HTMLPurifier/Injector.php @@ -17,64 +17,71 @@ abstract class HTMLPurifier_Injector { /** - * Advisory name of injector, this is for friendly error messages + * Advisory name of injector, this is for friendly error messages. + * @type string */ public $name; /** - * Instance of HTMLPurifier_HTMLDefinition + * @type HTMLPurifier_HTMLDefinition */ protected $htmlDefinition; /** * Reference to CurrentNesting variable in Context. This is an array * list of tokens that we are currently "inside" + * @type array */ protected $currentNesting; /** - * Reference to InputTokens variable in Context. This is an array - * list of the input tokens that are being processed. + * Reference to current token. + * @type HTMLPurifier_Token */ - protected $inputTokens; + protected $currentToken; /** - * Reference to InputIndex variable in Context. This is an integer - * array index for $this->inputTokens that indicates what token - * is currently being processed. + * Reference to InputZipper variable in Context. + * @type HTMLPurifier_Zipper */ - protected $inputIndex; + protected $inputZipper; /** * Array of elements and attributes this injector creates and therefore * need to be allowed by the definition. Takes form of * array('element' => array('attr', 'attr2'), 'element2') + * @type array */ public $needed = array(); /** - * Index of inputTokens to rewind to. + * Number of elements to rewind backwards (relative). + * @type bool|int */ - protected $rewind = false; + protected $rewindOffset = false; /** * Rewind to a spot to re-perform processing. This is useful if you * deleted a node, and now need to see if this change affected any * earlier nodes. Rewinding does not affect other injectors, and can * result in infinite loops if not used carefully. + * @param bool|int $offset * @warning HTML Purifier will prevent you from fast-forwarding with this * function. */ - public function rewind($index) { - $this->rewind = $index; + public function rewindOffset($offset) + { + $this->rewindOffset = $offset; } /** - * Retrieves rewind, and then unsets it. + * Retrieves rewind offset, and then unsets it. + * @return bool|int */ - public function getRewind() { - $r = $this->rewind; - $this->rewind = false; + public function getRewindOffset() + { + $r = $this->rewindOffset; + $this->rewindOffset = false; return $r; } @@ -83,20 +90,23 @@ abstract class HTMLPurifier_Injector * this allows references to important variables to be made within * the injector. This function also checks if the HTML environment * will work with the Injector (see checkNeeded()). - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @return Boolean false if success, string of missing needed element/attribute if failure + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string Boolean false if success, string of missing needed element/attribute if failure */ - public function prepare($config, $context) { + public function prepare($config, $context) + { $this->htmlDefinition = $config->getHTMLDefinition(); // Even though this might fail, some unit tests ignore this and // still test checkNeeded, so be careful. Maybe get rid of that // dependency. $result = $this->checkNeeded($config); - if ($result !== false) return $result; + if ($result !== false) { + return $result; + } $this->currentNesting =& $context->get('CurrentNesting'); - $this->inputTokens =& $context->get('InputTokens'); - $this->inputIndex =& $context->get('InputIndex'); + $this->currentToken =& $context->get('CurrentToken'); + $this->inputZipper =& $context->get('InputZipper'); return false; } @@ -104,18 +114,26 @@ abstract class HTMLPurifier_Injector * This function checks if the HTML environment * will work with the Injector: if p tags are not allowed, the * Auto-Paragraphing injector should not be enabled. - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @return Boolean false if success, string of missing needed element/attribute if failure + * @param HTMLPurifier_Config $config + * @return bool|string Boolean false if success, string of missing needed element/attribute if failure */ - public function checkNeeded($config) { + public function checkNeeded($config) + { $def = $config->getHTMLDefinition(); foreach ($this->needed as $element => $attributes) { - if (is_int($element)) $element = $attributes; - if (!isset($def->info[$element])) return $element; - if (!is_array($attributes)) continue; + if (is_int($element)) { + $element = $attributes; + } + if (!isset($def->info[$element])) { + return $element; + } + if (!is_array($attributes)) { + continue; + } foreach ($attributes as $name) { - if (!isset($def->info[$element]->attr[$name])) return "$element.$name"; + if (!isset($def->info[$element]->attr[$name])) { + return "$element.$name"; + } } } return false; @@ -123,10 +141,11 @@ abstract class HTMLPurifier_Injector /** * Tests if the context node allows a certain element - * @param $name Name of element to test for - * @return True if element is allowed, false if it is not + * @param string $name Name of element to test for + * @return bool True if element is allowed, false if it is not */ - public function allowsElement($name) { + public function allowsElement($name) + { if (!empty($this->currentNesting)) { $parent_token = array_pop($this->currentNesting); $this->currentNesting[] = $parent_token; @@ -141,7 +160,9 @@ abstract class HTMLPurifier_Injector for ($i = count($this->currentNesting) - 2; $i >= 0; $i--) { $node = $this->currentNesting[$i]; $def = $this->htmlDefinition->info[$node->name]; - if (isset($def->excludes[$name])) return false; + if (isset($def->excludes[$name])) { + return false; + } } return true; } @@ -151,14 +172,22 @@ abstract class HTMLPurifier_Injector * you reach the end of the input tokens. * @warning Please prevent previous references from interfering with this * functions by setting $i = null beforehand! - * @param &$i Current integer index variable for inputTokens - * @param &$current Current token variable. Do NOT use $token, as that variable is also a reference - */ - protected function forward(&$i, &$current) { - if ($i === null) $i = $this->inputIndex + 1; - else $i++; - if (!isset($this->inputTokens[$i])) return false; - $current = $this->inputTokens[$i]; + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @return bool + */ + protected function forward(&$i, &$current) + { + if ($i === null) { + $i = count($this->inputZipper->back) - 1; + } else { + $i--; + } + if ($i < 0) { + return false; + } + $current = $this->inputZipper->back[$i]; return true; } @@ -166,14 +195,27 @@ abstract class HTMLPurifier_Injector * Similar to _forward, but accepts a third parameter $nesting (which * should be initialized at 0) and stops when we hit the end tag * for the node $this->inputIndex starts in. + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @param int $nesting + * @return bool */ - protected function forwardUntilEndToken(&$i, &$current, &$nesting) { + protected function forwardUntilEndToken(&$i, &$current, &$nesting) + { $result = $this->forward($i, $current); - if (!$result) return false; - if ($nesting === null) $nesting = 0; - if ($current instanceof HTMLPurifier_Token_Start) $nesting++; - elseif ($current instanceof HTMLPurifier_Token_End) { - if ($nesting <= 0) return false; + if (!$result) { + return false; + } + if ($nesting === null) { + $nesting = 0; + } + if ($current instanceof HTMLPurifier_Token_Start) { + $nesting++; + } elseif ($current instanceof HTMLPurifier_Token_End) { + if ($nesting <= 0) { + return false; + } $nesting--; } return true; @@ -184,56 +226,56 @@ abstract class HTMLPurifier_Injector * you reach the beginning of input tokens. * @warning Please prevent previous references from interfering with this * functions by setting $i = null beforehand! - * @param &$i Current integer index variable for inputTokens - * @param &$current Current token variable. Do NOT use $token, as that variable is also a reference - */ - protected function backward(&$i, &$current) { - if ($i === null) $i = $this->inputIndex - 1; - else $i--; - if ($i < 0) return false; - $current = $this->inputTokens[$i]; - return true; - } - - /** - * Initializes the iterator at the current position. Use in a do {} while; - * loop to force the _forward and _backward functions to start at the - * current location. - * @warning Please prevent previous references from interfering with this - * functions by setting $i = null beforehand! - * @param &$i Current integer index variable for inputTokens - * @param &$current Current token variable. Do NOT use $token, as that variable is also a reference + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @return bool */ - protected function current(&$i, &$current) { - if ($i === null) $i = $this->inputIndex; - $current = $this->inputTokens[$i]; + protected function backward(&$i, &$current) + { + if ($i === null) { + $i = count($this->inputZipper->front) - 1; + } else { + $i--; + } + if ($i < 0) { + return false; + } + $current = $this->inputZipper->front[$i]; + return true; } /** * Handler that is called when a text token is processed */ - public function handleText(&$token) {} + public function handleText(&$token) + { + } /** * Handler that is called when a start or empty token is processed */ - public function handleElement(&$token) {} + public function handleElement(&$token) + { + } /** * Handler that is called when an end token is processed */ - public function handleEnd(&$token) { + public function handleEnd(&$token) + { $this->notifyEnd($token); } /** * Notifier that is called when an end token is processed + * @param HTMLPurifier_Token $token Current token variable. * @note This differs from handlers in that the token is read-only * @deprecated */ - public function notifyEnd($token) {} - - + public function notifyEnd($token) + { + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Injector/AutoParagraph.php b/library/HTMLPurifier/Injector/AutoParagraph.php index afa760892..4afdd128d 100644 --- a/library/HTMLPurifier/Injector/AutoParagraph.php +++ b/library/HTMLPurifier/Injector/AutoParagraph.php @@ -8,17 +8,31 @@ */ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector { - + /** + * @type string + */ public $name = 'AutoParagraph'; + + /** + * @type array + */ public $needed = array('p'); - private function _pStart() { + /** + * @return HTMLPurifier_Token_Start + */ + private function _pStart() + { $par = new HTMLPurifier_Token_Start('p'); $par->armor['MakeWellFormed_TagClosedError'] = true; return $par; } - public function handleText(&$token) { + /** + * @param HTMLPurifier_Token_Text $token + */ + public function handleText(&$token) + { $text = $token->data; // Does the current parent allow <p> tags? if ($this->allowsElement('p')) { @@ -72,11 +86,9 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector // ---- } } - // Is the current parent a <p> tag? - } elseif ( - !empty($this->currentNesting) && - $this->currentNesting[count($this->currentNesting)-1]->name == 'p' - ) { + // Is the current parent a <p> tag? + } elseif (!empty($this->currentNesting) && + $this->currentNesting[count($this->currentNesting) - 1]->name == 'p') { // State 3.1: ...<p>PAR1 // ---- @@ -84,7 +96,7 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector // ------------ $token = array(); $this->_splitText($text, $token); - // Abort! + // Abort! } else { // State 4.1: ...<b>PAR1 // ---- @@ -94,7 +106,11 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector } } - public function handleElement(&$token) { + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { // We don't have to check if we're already in a <p> tag for block // tokens, because the tag would have been autoclosed by MakeWellFormed. if ($this->allowsElement('p')) { @@ -102,7 +118,6 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector if ($this->_isInline($token)) { // State 1: <div>...<b> // --- - // Check if this token is adjacent to the parent token // (seek backwards until token isn't whitespace) $i = null; @@ -110,31 +125,24 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector if (!$prev instanceof HTMLPurifier_Token_Start) { // Token wasn't adjacent - - if ( - $prev instanceof HTMLPurifier_Token_Text && + if ($prev instanceof HTMLPurifier_Token_Text && substr($prev->data, -2) === "\n\n" ) { // State 1.1.4: <div><p>PAR1</p>\n\n<b> // --- - // Quite frankly, this should be handled by splitText $token = array($this->_pStart(), $token); } else { // State 1.1.1: <div><p>PAR1</p><b> // --- - // State 1.1.2: <div><br /><b> // --- - // State 1.1.3: <div>PAR<b> // --- } - } else { // State 1.2.1: <div><b> // --- - // Lookahead to see if <p> is needed. if ($this->_pLookAhead()) { // State 1.3.1: <div><b>PAR1\n\nPAR2 @@ -166,24 +174,20 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector $i = null; if ($this->backward($i, $prev)) { - if ( - !$prev instanceof HTMLPurifier_Token_Text - ) { + if (!$prev instanceof HTMLPurifier_Token_Text) { // State 3.1.1: ...</p>{p}<b> // --- - // State 3.2.1: ...</p><div> // ----- - - if (!is_array($token)) $token = array($token); + if (!is_array($token)) { + $token = array($token); + } array_unshift($token, new HTMLPurifier_Token_Text("\n\n")); } else { // State 3.1.2: ...</p>\n\n{p}<b> // --- - // State 3.2.2: ...</p>\n\n<div> // ----- - // Note: PAR<ELEM> cannot occur because PAR would have been // wrapped in <p> tags. } @@ -192,7 +196,6 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector } else { // State 2.2: <ul><li> // ---- - // State 2.4: <p><b> // --- } @@ -201,18 +204,17 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector /** * Splits up a text in paragraph tokens and appends them * to the result stream that will replace the original - * @param $data String text data that will be processed + * @param string $data String text data that will be processed * into paragraphs - * @param $result Reference to array of tokens that the + * @param HTMLPurifier_Token[] $result Reference to array of tokens that the * tags will be appended onto - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context */ - private function _splitText($data, &$result) { + private function _splitText($data, &$result) + { $raw_paragraphs = explode("\n\n", $data); - $paragraphs = array(); // without empty paragraphs + $paragraphs = array(); // without empty paragraphs $needs_start = false; - $needs_end = false; + $needs_end = false; $c = count($raw_paragraphs); if ($c == 1) { @@ -285,26 +287,33 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector array_pop($result); // removes \n\n array_pop($result); // removes </p> } - } /** * Returns true if passed token is inline (and, ergo, allowed in * paragraph tags) + * @param HTMLPurifier_Token $token + * @return bool */ - private function _isInline($token) { + private function _isInline($token) + { return isset($this->htmlDefinition->info['p']->child->elements[$token->name]); } /** * Looks ahead in the token list and determines whether or not we need * to insert a <p> tag. + * @return bool */ - private function _pLookAhead() { - $this->current($i, $current); - if ($current instanceof HTMLPurifier_Token_Start) $nesting = 1; - else $nesting = 0; + private function _pLookAhead() + { + if ($this->currentToken instanceof HTMLPurifier_Token_Start) { + $nesting = 1; + } else { + $nesting = 0; + } $ok = false; + $i = null; while ($this->forwardUntilEndToken($i, $current, $nesting)) { $result = $this->_checkNeedsP($current); if ($result !== null) { @@ -318,9 +327,12 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector /** * Determines if a particular token requires an earlier inline token * to get a paragraph. This should be used with _forwardUntilEndToken + * @param HTMLPurifier_Token $current + * @return bool */ - private function _checkNeedsP($current) { - if ($current instanceof HTMLPurifier_Token_Start){ + private function _checkNeedsP($current) + { + if ($current instanceof HTMLPurifier_Token_Start) { if (!$this->_isInline($current)) { // <div>PAR1<div> // ---- @@ -339,7 +351,6 @@ class HTMLPurifier_Injector_AutoParagraph extends HTMLPurifier_Injector } return null; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Injector/DisplayLinkURI.php b/library/HTMLPurifier/Injector/DisplayLinkURI.php index 9dce9bd08..c19b1bc27 100644 --- a/library/HTMLPurifier/Injector/DisplayLinkURI.php +++ b/library/HTMLPurifier/Injector/DisplayLinkURI.php @@ -5,15 +5,29 @@ */ class HTMLPurifier_Injector_DisplayLinkURI extends HTMLPurifier_Injector { - + /** + * @type string + */ public $name = 'DisplayLinkURI'; + + /** + * @type array + */ public $needed = array('a'); - public function handleElement(&$token) { + /** + * @param $token + */ + public function handleElement(&$token) + { } - public function handleEnd(&$token) { - if (isset($token->start->attr['href'])){ + /** + * @param HTMLPurifier_Token $token + */ + public function handleEnd(&$token) + { + if (isset($token->start->attr['href'])) { $url = $token->start->attr['href']; unset($token->start->attr['href']); $token = array($token, new HTMLPurifier_Token_Text(" ($url)")); diff --git a/library/HTMLPurifier/Injector/Linkify.php b/library/HTMLPurifier/Injector/Linkify.php index 296dac282..069708c25 100644 --- a/library/HTMLPurifier/Injector/Linkify.php +++ b/library/HTMLPurifier/Injector/Linkify.php @@ -5,12 +5,24 @@ */ class HTMLPurifier_Injector_Linkify extends HTMLPurifier_Injector { - + /** + * @type string + */ public $name = 'Linkify'; + + /** + * @type array + */ public $needed = array('a' => array('href')); - public function handleText(&$token) { - if (!$this->allowsElement('a')) return; + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } if (strpos($token->data, '://') === false) { // our really quick heuristic failed, abort @@ -21,7 +33,8 @@ class HTMLPurifier_Injector_Linkify extends HTMLPurifier_Injector // there is/are URL(s). Let's split the string: // Note: this regex is extremely permissive - $bits = preg_split('#((?:https?|ftp)://[^\s\'"<>()]+)#S', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + $bits = preg_split('#((?:https?|ftp)://[^\s\'",<>()]+)#Su', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + $token = array(); @@ -30,7 +43,9 @@ class HTMLPurifier_Injector_Linkify extends HTMLPurifier_Injector // $l = is link for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { if (!$l) { - if ($bits[$i] === '') continue; + if ($bits[$i] === '') { + continue; + } $token[] = new HTMLPurifier_Token_Text($bits[$i]); } else { $token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i])); @@ -38,9 +53,7 @@ class HTMLPurifier_Injector_Linkify extends HTMLPurifier_Injector $token[] = new HTMLPurifier_Token_End('a'); } } - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Injector/PurifierLinkify.php b/library/HTMLPurifier/Injector/PurifierLinkify.php index ad2455a91..cb9046f33 100644 --- a/library/HTMLPurifier/Injector/PurifierLinkify.php +++ b/library/HTMLPurifier/Injector/PurifierLinkify.php @@ -6,19 +6,43 @@ */ class HTMLPurifier_Injector_PurifierLinkify extends HTMLPurifier_Injector { - + /** + * @type string + */ public $name = 'PurifierLinkify'; + + /** + * @type string + */ public $docURL; + + /** + * @type array + */ public $needed = array('a' => array('href')); - public function prepare($config, $context) { + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function prepare($config, $context) + { $this->docURL = $config->get('AutoFormat.PurifierLinkify.DocURL'); return parent::prepare($config, $context); } - public function handleText(&$token) { - if (!$this->allowsElement('a')) return; - if (strpos($token->data, '%') === false) return; + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + if (strpos($token->data, '%') === false) { + return; + } $bits = preg_split('#%([a-z0-9]+\.[a-z0-9]+)#Si', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); $token = array(); @@ -28,18 +52,20 @@ class HTMLPurifier_Injector_PurifierLinkify extends HTMLPurifier_Injector // $l = is link for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { if (!$l) { - if ($bits[$i] === '') continue; + if ($bits[$i] === '') { + continue; + } $token[] = new HTMLPurifier_Token_Text($bits[$i]); } else { - $token[] = new HTMLPurifier_Token_Start('a', - array('href' => str_replace('%s', $bits[$i], $this->docURL))); + $token[] = new HTMLPurifier_Token_Start( + 'a', + array('href' => str_replace('%s', $bits[$i], $this->docURL)) + ); $token[] = new HTMLPurifier_Token_Text('%' . $bits[$i]); $token[] = new HTMLPurifier_Token_End('a'); } } - } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Injector/RemoveEmpty.php b/library/HTMLPurifier/Injector/RemoveEmpty.php index 638bfca03..cd885722e 100644 --- a/library/HTMLPurifier/Injector/RemoveEmpty.php +++ b/library/HTMLPurifier/Injector/RemoveEmpty.php @@ -2,10 +2,44 @@ class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector { + /** + * @type HTMLPurifier_Context + */ + private $context; - private $context, $config, $attrValidator, $removeNbsp, $removeNbspExceptions; + /** + * @type HTMLPurifier_Config + */ + private $config; - public function prepare($config, $context) { + /** + * @type HTMLPurifier_AttrValidator + */ + private $attrValidator; + + /** + * @type bool + */ + private $removeNbsp; + + /** + * @type bool + */ + private $removeNbspExceptions; + + /** + * @type array + * TODO: make me configurable + */ + private $_exclude = array('colgroup' => 1, 'th' => 1, 'td' => 1, 'iframe' => 1); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return void + */ + public function prepare($config, $context) + { parent::prepare($config, $context); $this->config = $config; $this->context = $context; @@ -14,38 +48,54 @@ class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector $this->attrValidator = new HTMLPurifier_AttrValidator(); } - public function handleElement(&$token) { - if (!$token instanceof HTMLPurifier_Token_Start) return; + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if (!$token instanceof HTMLPurifier_Token_Start) { + return; + } $next = false; - for ($i = $this->inputIndex + 1, $c = count($this->inputTokens); $i < $c; $i++) { - $next = $this->inputTokens[$i]; + $deleted = 1; // the current tag + for ($i = count($this->inputZipper->back) - 1; $i >= 0; $i--, $deleted++) { + $next = $this->inputZipper->back[$i]; if ($next instanceof HTMLPurifier_Token_Text) { - if ($next->is_whitespace) continue; + if ($next->is_whitespace) { + continue; + } if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) { $plain = str_replace("\xC2\xA0", "", $next->data); $isWsOrNbsp = $plain === '' || ctype_space($plain); - if ($isWsOrNbsp) continue; + if ($isWsOrNbsp) { + continue; + } } } break; } if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) { - if ($token->name == 'colgroup') return; + if (isset($this->_exclude[$token->name])) { + return; + } $this->attrValidator->validateToken($token, $this->config, $this->context); $token->armor['ValidateAttributes'] = true; - if (isset($token->attr['id']) || isset($token->attr['name'])) return; - $token = $i - $this->inputIndex + 1; - for ($b = $this->inputIndex - 1; $b > 0; $b--) { - $prev = $this->inputTokens[$b]; - if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) continue; + if (isset($token->attr['id']) || isset($token->attr['name'])) { + return; + } + $token = $deleted + 1; + for ($b = 0, $c = count($this->inputZipper->front); $b < $c; $b++) { + $prev = $this->inputZipper->front[$b]; + if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) { + continue; + } break; } // This is safe because we removed the token that triggered this. - $this->rewind($b - 1); + $this->rewindOffset($b+$deleted); return; } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php b/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php index b21313470..9ee7aa84d 100644 --- a/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php +++ b/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php @@ -5,25 +5,45 @@ */ class HTMLPurifier_Injector_RemoveSpansWithoutAttributes extends HTMLPurifier_Injector { + /** + * @type string + */ public $name = 'RemoveSpansWithoutAttributes'; + + /** + * @type array + */ public $needed = array('span'); + /** + * @type HTMLPurifier_AttrValidator + */ private $attrValidator; /** - * Used by AttrValidator + * Used by AttrValidator. + * @type HTMLPurifier_Config */ private $config; + + /** + * @type HTMLPurifier_Context + */ private $context; - public function prepare($config, $context) { + public function prepare($config, $context) + { $this->attrValidator = new HTMLPurifier_AttrValidator(); $this->config = $config; $this->context = $context; return parent::prepare($config, $context); } - public function handleElement(&$token) { + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { if ($token->name !== 'span' || !$token instanceof HTMLPurifier_Token_Start) { return; } @@ -39,8 +59,8 @@ class HTMLPurifier_Injector_RemoveSpansWithoutAttributes extends HTMLPurifier_In } $nesting = 0; - $spanContentTokens = array(); - while ($this->forwardUntilEndToken($i, $current, $nesting)) {} + while ($this->forwardUntilEndToken($i, $current, $nesting)) { + } if ($current instanceof HTMLPurifier_Token_End && $current->name === 'span') { // Mark closing span tag for deletion @@ -50,7 +70,11 @@ class HTMLPurifier_Injector_RemoveSpansWithoutAttributes extends HTMLPurifier_In } } - public function handleEnd(&$token) { + /** + * @param HTMLPurifier_Token $token + */ + public function handleEnd(&$token) + { if ($token->markForDeletion) { $token = false; } diff --git a/library/HTMLPurifier/Injector/SafeObject.php b/library/HTMLPurifier/Injector/SafeObject.php index 9e178ce01..3d17e07af 100644 --- a/library/HTMLPurifier/Injector/SafeObject.php +++ b/library/HTMLPurifier/Injector/SafeObject.php @@ -6,29 +6,61 @@ */ class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector { + /** + * @type string + */ public $name = 'SafeObject'; + + /** + * @type array + */ public $needed = array('object', 'param'); + /** + * @type array + */ protected $objectStack = array(); - protected $paramStack = array(); - // Keep this synchronized with AttrTransform/SafeParam.php + /** + * @type array + */ + protected $paramStack = array(); + + /** + * Keep this synchronized with AttrTransform/SafeParam.php. + * @type array + */ protected $addParam = array( 'allowScriptAccess' => 'never', 'allowNetworking' => 'internal', ); + + /** + * @type array + */ protected $allowedParam = array( 'wmode' => true, 'movie' => true, 'flashvars' => true, 'src' => true, + 'allowFullScreen' => true, // if omitted, assume to be 'false' ); - public function prepare($config, $context) { + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return void + */ + public function prepare($config, $context) + { parent::prepare($config, $context); } - public function handleElement(&$token) { + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { if ($token->name == 'object') { $this->objectStack[] = $token; $this->paramStack[] = array(); @@ -50,16 +82,15 @@ class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector // attribute, which we need if a type is specified. This is // *very* Flash specific. if (!isset($this->objectStack[$i]->attr['data']) && - ($token->attr['name'] == 'movie' || $token->attr['name'] == 'src')) { + ($token->attr['name'] == 'movie' || $token->attr['name'] == 'src') + ) { $this->objectStack[$i]->attr['data'] = $token->attr['value']; } // Check if the parameter is the correct value but has not // already been added - if ( - !isset($this->paramStack[$i][$n]) && + if (!isset($this->paramStack[$i][$n]) && isset($this->addParam[$n]) && - $token->attr['name'] === $this->addParam[$n] - ) { + $token->attr['name'] === $this->addParam[$n]) { // keep token, and add to param stack $this->paramStack[$i][$n] = true; } elseif (isset($this->allowedParam[$n])) { @@ -75,7 +106,8 @@ class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector } } - public function handleEnd(&$token) { + public function handleEnd(&$token) + { // This is the WRONG way of handling the object and param stacks; // we should be inserting them directly on the relevant object tokens // so that the global stack handling handles it. @@ -84,7 +116,6 @@ class HTMLPurifier_Injector_SafeObject extends HTMLPurifier_Injector array_pop($this->paramStack); } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Language.php b/library/HTMLPurifier/Language.php index 3e2be03b5..65277dd43 100644 --- a/library/HTMLPurifier/Language.php +++ b/library/HTMLPurifier/Language.php @@ -8,22 +8,26 @@ class HTMLPurifier_Language { /** - * ISO 639 language code of language. Prefers shortest possible version + * ISO 639 language code of language. Prefers shortest possible version. + * @type string */ public $code = 'en'; /** - * Fallback language code + * Fallback language code. + * @type bool|string */ public $fallback = false; /** - * Array of localizable messages + * Array of localizable messages. + * @type array */ public $messages = array(); /** - * Array of localizable error codes + * Array of localizable error codes. + * @type array */ public $errorNames = array(); @@ -31,21 +35,33 @@ class HTMLPurifier_Language * True if no message file was found for this language, so English * is being used instead. Check this if you'd like to notify the * user that they've used a non-supported language. + * @type bool */ public $error = false; /** * Has the language object been loaded yet? + * @type bool * @todo Make it private, fix usage in HTMLPurifier_LanguageTest */ public $_loaded = false; /** - * Instances of HTMLPurifier_Config and HTMLPurifier_Context + * @type HTMLPurifier_Config */ - protected $config, $context; + protected $config; - public function __construct($config, $context) { + /** + * @type HTMLPurifier_Context + */ + protected $context; + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + public function __construct($config, $context) + { $this->config = $config; $this->context = $context; } @@ -54,8 +70,11 @@ class HTMLPurifier_Language * Loads language object with necessary info from factory cache * @note This is a lazy loader */ - public function load() { - if ($this->_loaded) return; + public function load() + { + if ($this->_loaded) { + return; + } $factory = HTMLPurifier_LanguageFactory::instance(); $factory->loadLanguage($this->code); foreach ($factory->keys as $key) { @@ -66,31 +85,43 @@ class HTMLPurifier_Language /** * Retrieves a localised message. - * @param $key string identifier of message + * @param string $key string identifier of message * @return string localised message */ - public function getMessage($key) { - if (!$this->_loaded) $this->load(); - if (!isset($this->messages[$key])) return "[$key]"; + public function getMessage($key) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } return $this->messages[$key]; } /** * Retrieves a localised error name. - * @param $int integer error number, corresponding to PHP's error - * reporting + * @param int $int error number, corresponding to PHP's error reporting * @return string localised message */ - public function getErrorName($int) { - if (!$this->_loaded) $this->load(); - if (!isset($this->errorNames[$int])) return "[Error: $int]"; + public function getErrorName($int) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->errorNames[$int])) { + return "[Error: $int]"; + } return $this->errorNames[$int]; } /** * Converts an array list into a string readable representation + * @param array $array + * @return string */ - public function listify($array) { + public function listify($array) + { $sep = $this->getMessage('Item separator'); $sep_last = $this->getMessage('Item separator last'); $ret = ''; @@ -108,15 +139,20 @@ class HTMLPurifier_Language /** * Formats a localised message with passed parameters - * @param $key string identifier of message - * @param $args Parameters to substitute in + * @param string $key string identifier of message + * @param array $args Parameters to substitute in * @return string localised message * @todo Implement conditionals? Right now, some messages make * reference to line numbers, but those aren't always available */ - public function formatMessage($key, $args = array()) { - if (!$this->_loaded) $this->load(); - if (!isset($this->messages[$key])) return "[$key]"; + public function formatMessage($key, $args = array()) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } $raw = $this->messages[$key]; $subst = array(); $generator = false; @@ -124,9 +160,15 @@ class HTMLPurifier_Language if (is_object($value)) { if ($value instanceof HTMLPurifier_Token) { // factor this out some time - if (!$generator) $generator = $this->context->get('Generator'); - if (isset($value->name)) $subst['$'.$i.'.Name'] = $value->name; - if (isset($value->data)) $subst['$'.$i.'.Data'] = $value->data; + if (!$generator) { + $generator = $this->context->get('Generator'); + } + if (isset($value->name)) { + $subst['$'.$i.'.Name'] = $value->name; + } + if (isset($value->data)) { + $subst['$'.$i.'.Data'] = $value->data; + } $subst['$'.$i.'.Compact'] = $subst['$'.$i.'.Serialized'] = $generator->generateFromToken($value); // a more complex algorithm for compact representation @@ -157,7 +199,6 @@ class HTMLPurifier_Language } return strtr($raw, $subst); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Language/classes/en-x-test.php b/library/HTMLPurifier/Language/classes/en-x-test.php index d52fcb7ac..8828f5cde 100644 --- a/library/HTMLPurifier/Language/classes/en-x-test.php +++ b/library/HTMLPurifier/Language/classes/en-x-test.php @@ -4,9 +4,6 @@ class HTMLPurifier_Language_en_x_test extends HTMLPurifier_Language { - - - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Language/messages/en.php b/library/HTMLPurifier/Language/messages/en.php index 8d7b5736b..c7f197e1e 100644 --- a/library/HTMLPurifier/Language/messages/en.php +++ b/library/HTMLPurifier/Language/messages/en.php @@ -4,60 +4,52 @@ $fallback = false; $messages = array( -'HTMLPurifier' => 'HTML Purifier', - + 'HTMLPurifier' => 'HTML Purifier', // for unit testing purposes -'LanguageFactoryTest: Pizza' => 'Pizza', -'LanguageTest: List' => '$1', -'LanguageTest: Hash' => '$1.Keys; $1.Values', - -'Item separator' => ', ', -'Item separator last' => ' and ', // non-Harvard style - -'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.', -'ErrorCollector: At line' => ' at line $line', -'ErrorCollector: Incidental errors' => 'Incidental errors', - -'Lexer: Unclosed comment' => 'Unclosed comment', -'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <', -'Lexer: Missing gt' => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped', -'Lexer: Missing attribute key' => 'Attribute declaration has no key', -'Lexer: Missing end quote' => 'Attribute declaration has no end quote', -'Lexer: Extracted body' => 'Removed document metadata tags', - -'Strategy_RemoveForeignElements: Tag transform' => '<$1> element transformed into $CurrentToken.Serialized', -'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1', -'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text', -'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed', -'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed', -'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed', -'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end', -'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed', -'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens', - -'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed', -'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text', -'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact', -'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact', -'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed', -'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text', -'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized', -'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document', - -'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed', -'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element', -'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model', -'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed', - -'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys', -'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed', - + 'LanguageFactoryTest: Pizza' => 'Pizza', + 'LanguageTest: List' => '$1', + 'LanguageTest: Hash' => '$1.Keys; $1.Values', + 'Item separator' => ', ', + 'Item separator last' => ' and ', // non-Harvard style + + 'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.', + 'ErrorCollector: At line' => ' at line $line', + 'ErrorCollector: Incidental errors' => 'Incidental errors', + 'Lexer: Unclosed comment' => 'Unclosed comment', + 'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <', + 'Lexer: Missing gt' => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped', + 'Lexer: Missing attribute key' => 'Attribute declaration has no key', + 'Lexer: Missing end quote' => 'Attribute declaration has no end quote', + 'Lexer: Extracted body' => 'Removed document metadata tags', + 'Strategy_RemoveForeignElements: Tag transform' => '<$1> element transformed into $CurrentToken.Serialized', + 'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1', + 'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text', + 'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed', + 'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed', + 'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed', + 'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end', + 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed', + 'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens', + 'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized', + 'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document', + 'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed', + 'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element', + 'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model', + 'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed', + 'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys', + 'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed', ); $errorNames = array( - E_ERROR => 'Error', + E_ERROR => 'Error', E_WARNING => 'Warning', - E_NOTICE => 'Notice' + E_NOTICE => 'Notice' ); // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/LanguageFactory.php b/library/HTMLPurifier/LanguageFactory.php index 134ef8c74..4e35272d8 100644 --- a/library/HTMLPurifier/LanguageFactory.php +++ b/library/HTMLPurifier/LanguageFactory.php @@ -11,50 +11,53 @@ class HTMLPurifier_LanguageFactory { /** - * Cache of language code information used to load HTMLPurifier_Language objects + * Cache of language code information used to load HTMLPurifier_Language objects. * Structure is: $factory->cache[$language_code][$key] = $value - * @value array map + * @type array */ public $cache; /** * Valid keys in the HTMLPurifier_Language object. Designates which * variables to slurp out of a message file. - * @value array list + * @type array */ public $keys = array('fallback', 'messages', 'errorNames'); /** - * Instance of HTMLPurifier_AttrDef_Lang to validate language codes - * @value object HTMLPurifier_AttrDef_Lang + * Instance to validate language codes. + * @type HTMLPurifier_AttrDef_Lang + * */ protected $validator; /** * Cached copy of dirname(__FILE__), directory of current file without - * trailing slash - * @value string filename + * trailing slash. + * @type string */ protected $dir; /** - * Keys whose contents are a hash map and can be merged - * @value array lookup + * Keys whose contents are a hash map and can be merged. + * @type array */ protected $mergeable_keys_map = array('messages' => true, 'errorNames' => true); /** - * Keys whose contents are a list and can be merged + * Keys whose contents are a list and can be merged. * @value array lookup */ protected $mergeable_keys_list = array(); /** * Retrieve sole instance of the factory. - * @param $prototype Optional prototype to overload sole instance with, + * @param HTMLPurifier_LanguageFactory $prototype Optional prototype to overload sole instance with, * or bool true to reset to default factory. + * @return HTMLPurifier_LanguageFactory */ - public static function instance($prototype = null) { + public static function instance($prototype = null) + { static $instance = null; if ($prototype !== null) { $instance = $prototype; @@ -69,28 +72,34 @@ class HTMLPurifier_LanguageFactory * Sets up the singleton, much like a constructor * @note Prevents people from getting this outside of the singleton */ - public function setup() { + public function setup() + { $this->validator = new HTMLPurifier_AttrDef_Lang(); $this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier'; } /** * Creates a language object, handles class fallbacks - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @param $code Code to override configuration with. Private parameter. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @param bool|string $code Code to override configuration with. Private parameter. + * @return HTMLPurifier_Language */ - public function create($config, $context, $code = false) { - + public function create($config, $context, $code = false) + { // validate language code if ($code === false) { $code = $this->validator->validate( - $config->get('Core.Language'), $config, $context + $config->get('Core.Language'), + $config, + $context ); } else { $code = $this->validator->validate($code, $config, $context); } - if ($code === false) $code = 'en'; // malformed code becomes English + if ($code === false) { + $code = 'en'; // malformed code becomes English + } $pcode = str_replace('-', '_', $code); // make valid PHP classname static $depth = 0; // recursion protection @@ -114,32 +123,34 @@ class HTMLPurifier_LanguageFactory $depth--; } } - $lang->code = $code; - return $lang; - } /** * Returns the fallback language for language * @note Loads the original language into cache - * @param $code string language code + * @param string $code language code + * @return string|bool */ - public function getFallbackFor($code) { + public function getFallbackFor($code) + { $this->loadLanguage($code); return $this->cache[$code]['fallback']; } /** * Loads language into the cache, handles message file and fallbacks - * @param $code string language code + * @param string $code language code */ - public function loadLanguage($code) { + public function loadLanguage($code) + { static $languages_seen = array(); // recursion guard // abort if we've already loaded it - if (isset($this->cache[$code])) return; + if (isset($this->cache[$code])) { + return; + } // generate filename $filename = $this->dir . '/Language/messages/' . $code . '.php'; @@ -162,8 +173,11 @@ class HTMLPurifier_LanguageFactory // infinite recursion guard if (isset($languages_seen[$code])) { - trigger_error('Circular fallback reference in language ' . - $code, E_USER_ERROR); + trigger_error( + 'Circular fallback reference in language ' . + $code, + E_USER_ERROR + ); $fallback = 'en'; } $language_seen[$code] = true; @@ -173,26 +187,23 @@ class HTMLPurifier_LanguageFactory $fallback_cache = $this->cache[$fallback]; // merge fallback with current language - foreach ( $this->keys as $key ) { + foreach ($this->keys as $key) { if (isset($cache[$key]) && isset($fallback_cache[$key])) { if (isset($this->mergeable_keys_map[$key])) { $cache[$key] = $cache[$key] + $fallback_cache[$key]; } elseif (isset($this->mergeable_keys_list[$key])) { - $cache[$key] = array_merge( $fallback_cache[$key], $cache[$key] ); + $cache[$key] = array_merge($fallback_cache[$key], $cache[$key]); } } else { $cache[$key] = $fallback_cache[$key]; } } - } // save to cache for later retrieval $this->cache[$code] = $cache; - return; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Length.php b/library/HTMLPurifier/Length.php index 8d2a46b7d..bbfbe6624 100644 --- a/library/HTMLPurifier/Length.php +++ b/library/HTMLPurifier/Length.php @@ -9,21 +9,25 @@ class HTMLPurifier_Length /** * String numeric magnitude. + * @type string */ protected $n; /** * String unit. False is permitted if $n = 0. + * @type string|bool */ protected $unit; /** * Whether or not this length is valid. Null if not calculated yet. + * @type bool */ protected $isValid; /** - * Lookup array of units recognized by CSS 2.1 + * Array Lookup array of units recognized by CSS 2.1 + * @type array */ protected static $allowedUnits = array( 'em' => true, 'ex' => true, 'px' => true, 'in' => true, @@ -31,85 +35,126 @@ class HTMLPurifier_Length ); /** - * @param number $n Magnitude - * @param string $u Unit + * @param string $n Magnitude + * @param bool|string $u Unit */ - public function __construct($n = '0', $u = false) { + public function __construct($n = '0', $u = false) + { $this->n = (string) $n; $this->unit = $u !== false ? (string) $u : false; } /** * @param string $s Unit string, like '2em' or '3.4in' + * @return HTMLPurifier_Length * @warning Does not perform validation. */ - static public function make($s) { - if ($s instanceof HTMLPurifier_Length) return $s; + public static function make($s) + { + if ($s instanceof HTMLPurifier_Length) { + return $s; + } $n_length = strspn($s, '1234567890.+-'); $n = substr($s, 0, $n_length); $unit = substr($s, $n_length); - if ($unit === '') $unit = false; + if ($unit === '') { + $unit = false; + } return new HTMLPurifier_Length($n, $unit); } /** * Validates the number and unit. + * @return bool */ - protected function validate() { + protected function validate() + { // Special case: - if ($this->n === '+0' || $this->n === '-0') $this->n = '0'; - if ($this->n === '0' && $this->unit === false) return true; - if (!ctype_lower($this->unit)) $this->unit = strtolower($this->unit); - if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) return false; + if ($this->n === '+0' || $this->n === '-0') { + $this->n = '0'; + } + if ($this->n === '0' && $this->unit === false) { + return true; + } + if (!ctype_lower($this->unit)) { + $this->unit = strtolower($this->unit); + } + if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) { + return false; + } // Hack: $def = new HTMLPurifier_AttrDef_CSS_Number(); $result = $def->validate($this->n, false, false); - if ($result === false) return false; + if ($result === false) { + return false; + } $this->n = $result; return true; } /** * Returns string representation of number. + * @return string */ - public function toString() { - if (!$this->isValid()) return false; + public function toString() + { + if (!$this->isValid()) { + return false; + } return $this->n . $this->unit; } /** * Retrieves string numeric magnitude. + * @return string */ - public function getN() {return $this->n;} + public function getN() + { + return $this->n; + } /** * Retrieves string unit. + * @return string */ - public function getUnit() {return $this->unit;} + public function getUnit() + { + return $this->unit; + } /** * Returns true if this length unit is valid. + * @return bool */ - public function isValid() { - if ($this->isValid === null) $this->isValid = $this->validate(); + public function isValid() + { + if ($this->isValid === null) { + $this->isValid = $this->validate(); + } return $this->isValid; } /** * Compares two lengths, and returns 1 if greater, -1 if less and 0 if equal. + * @param HTMLPurifier_Length $l + * @return int * @warning If both values are too large or small, this calculation will * not work properly */ - public function compareTo($l) { - if ($l === false) return false; + public function compareTo($l) + { + if ($l === false) { + return false; + } if ($l->unit !== $this->unit) { $converter = new HTMLPurifier_UnitConverter(); $l = $converter->convert($l, $this->unit); - if ($l === false) return false; + if ($l === false) { + return false; + } } return $this->n - $l->n; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Lexer.php b/library/HTMLPurifier/Lexer.php index b05e11546..43732621d 100644 --- a/library/HTMLPurifier/Lexer.php +++ b/library/HTMLPurifier/Lexer.php @@ -62,16 +62,20 @@ class HTMLPurifier_Lexer * To specify your own prototype, set %Core.LexerImpl to it. * This change in behavior de-singletonizes the lexer object. * - * @param $config Instance of HTMLPurifier_Config - * @return Concrete lexer. + * @param HTMLPurifier_Config $config + * @return HTMLPurifier_Lexer + * @throws HTMLPurifier_Exception */ - public static function create($config) { - + public static function create($config) + { if (!($config instanceof HTMLPurifier_Config)) { $lexer = $config; - trigger_error("Passing a prototype to - HTMLPurifier_Lexer::create() is deprecated, please instead - use %Core.LexerImpl", E_USER_WARNING); + trigger_error( + "Passing a prototype to + HTMLPurifier_Lexer::create() is deprecated, please instead + use %Core.LexerImpl", + E_USER_WARNING + ); } else { $lexer = $config->get('Core.LexerImpl'); } @@ -84,30 +88,28 @@ class HTMLPurifier_Lexer if (is_object($lexer)) { $inst = $lexer; } else { - - if (is_null($lexer)) { do { - // auto-detection algorithm - - if ($needs_tracking) { - $lexer = 'DirectLex'; - break; - } - - if ( - class_exists('DOMDocument') && - method_exists('DOMDocument', 'loadHTML') && - !extension_loaded('domxml') - ) { - // check for DOM support, because while it's part of the - // core, it can be disabled compile time. Also, the PECL - // domxml extension overrides the default DOM, and is evil - // and nasty and we shan't bother to support it - $lexer = 'DOMLex'; - } else { - $lexer = 'DirectLex'; - } - - } while(0); } // do..while so we can break + if (is_null($lexer)) { + do { + // auto-detection algorithm + if ($needs_tracking) { + $lexer = 'DirectLex'; + break; + } + + if (class_exists('DOMDocument') && + method_exists('DOMDocument', 'loadHTML') && + !extension_loaded('domxml') + ) { + // check for DOM support, because while it's part of the + // core, it can be disabled compile time. Also, the PECL + // domxml extension overrides the default DOM, and is evil + // and nasty and we shan't bother to support it + $lexer = 'DOMLex'; + } else { + $lexer = 'DirectLex'; + } + } while (0); + } // do..while so we can break // instantiate recognized string names switch ($lexer) { @@ -121,16 +123,24 @@ class HTMLPurifier_Lexer $inst = new HTMLPurifier_Lexer_PH5P(); break; default: - throw new HTMLPurifier_Exception("Cannot instantiate unrecognized Lexer type " . htmlspecialchars($lexer)); + throw new HTMLPurifier_Exception( + "Cannot instantiate unrecognized Lexer type " . + htmlspecialchars($lexer) + ); } } - if (!$inst) throw new HTMLPurifier_Exception('No lexer was instantiated'); + if (!$inst) { + throw new HTMLPurifier_Exception('No lexer was instantiated'); + } // once PHP DOM implements native line numbers, or we // hack out something using XSLT, remove this stipulation if ($needs_tracking && !$inst->tracksLineNumbers) { - throw new HTMLPurifier_Exception('Cannot use lexer that does not support line numbers with Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)'); + throw new HTMLPurifier_Exception( + 'Cannot use lexer that does not support line numbers with ' . + 'Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)' + ); } return $inst; @@ -139,23 +149,25 @@ class HTMLPurifier_Lexer // -- CONVENIENCE MEMBERS --------------------------------------------- - public function __construct() { + public function __construct() + { $this->_entity_parser = new HTMLPurifier_EntityParser(); } /** * Most common entity to raw value conversion table for special entities. + * @type array */ protected $_special_entity2str = - array( - '"' => '"', - '&' => '&', - '<' => '<', - '>' => '>', - ''' => "'", - ''' => "'", - ''' => "'" - ); + array( + '"' => '"', + '&' => '&', + '<' => '<', + '>' => '>', + ''' => "'", + ''' => "'", + ''' => "'" + ); /** * Parses special entities into the proper characters. @@ -168,27 +180,33 @@ class HTMLPurifier_Lexer * completely parsed, but that's only because all other entities should * have been handled previously in substituteNonSpecialEntities() * - * @param $string String character data to be parsed. - * @returns Parsed character data. + * @param string $string String character data to be parsed. + * @return string Parsed character data. */ - public function parseData($string) { - + public function parseData($string) + { // following functions require at least one character - if ($string === '') return ''; + if ($string === '') { + return ''; + } // subtracts amps that cannot possibly be escaped $num_amp = substr_count($string, '&') - substr_count($string, '& ') - - ($string[strlen($string)-1] === '&' ? 1 : 0); + ($string[strlen($string) - 1] === '&' ? 1 : 0); - if (!$num_amp) return $string; // abort if no entities + if (!$num_amp) { + return $string; + } // abort if no entities $num_esc_amp = substr_count($string, '&'); $string = strtr($string, $this->_special_entity2str); // code duplication for sake of optimization, see above $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') - - ($string[strlen($string)-1] === '&' ? 1 : 0); + ($string[strlen($string) - 1] === '&' ? 1 : 0); - if ($num_amp_2 <= $num_esc_amp) return $string; + if ($num_amp_2 <= $num_esc_amp) { + return $string; + } // hmm... now we have some uncommon entities. Use the callback. $string = $this->_entity_parser->substituteSpecialEntities($string); @@ -197,21 +215,23 @@ class HTMLPurifier_Lexer /** * Lexes an HTML string into tokens. - * * @param $string String HTML. - * @return HTMLPurifier_Token array representation of HTML. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] array representation of HTML. */ - public function tokenizeHTML($string, $config, $context) { + public function tokenizeHTML($string, $config, $context) + { trigger_error('Call to abstract class', E_USER_ERROR); } /** * Translates CDATA sections into regular sections (through escaping). - * - * @param $string HTML string to process. - * @returns HTML with CDATA sections escaped. + * @param string $string HTML string to process. + * @return string HTML with CDATA sections escaped. */ - protected static function escapeCDATA($string) { + protected static function escapeCDATA($string) + { return preg_replace_callback( '/<!\[CDATA\[(.+?)\]\]>/s', array('HTMLPurifier_Lexer', 'CDATACallback'), @@ -221,8 +241,11 @@ class HTMLPurifier_Lexer /** * Special CDATA case that is especially convoluted for <script> + * @param string $string HTML string to process. + * @return string HTML with CDATA sections escaped. */ - protected static function escapeCommentedCDATA($string) { + protected static function escapeCommentedCDATA($string) + { return preg_replace_callback( '#<!--//--><!\[CDATA\[//><!--(.+?)//--><!\]\]>#s', array('HTMLPurifier_Lexer', 'CDATACallback'), @@ -231,15 +254,30 @@ class HTMLPurifier_Lexer } /** + * Special Internet Explorer conditional comments should be removed. + * @param string $string HTML string to process. + * @return string HTML with conditional comments removed. + */ + protected static function removeIEConditional($string) + { + return preg_replace( + '#<!--\[if [^>]+\]>.*?<!\[endif\]-->#si', // probably should generalize for all strings + '', + $string + ); + } + + /** * Callback function for escapeCDATA() that does the work. * * @warning Though this is public in order to let the callback happen, * calling it directly is not recommended. - * @params $matches PCRE matches array, with index 0 the entire match + * @param array $matches PCRE matches array, with index 0 the entire match * and 1 the inside of the CDATA section. - * @returns Escaped internals of the CDATA section. + * @return string Escaped internals of the CDATA section. */ - protected static function CDATACallback($matches) { + protected static function CDATACallback($matches) + { // not exactly sure why the character set is needed, but whatever return htmlspecialchars($matches[1], ENT_COMPAT, 'UTF-8'); } @@ -247,13 +285,19 @@ class HTMLPurifier_Lexer /** * Takes a piece of HTML and normalizes it by converting entities, fixing * encoding, extracting bits, and other good stuff. + * @param string $html HTML. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string * @todo Consider making protected */ - public function normalize($html, $config, $context) { - + public function normalize($html, $config, $context) + { // normalize newlines to \n - $html = str_replace("\r\n", "\n", $html); - $html = str_replace("\r", "\n", $html); + if ($config->get('Core.NormalizeNewlines')) { + $html = str_replace("\r\n", "\n", $html); + $html = str_replace("\r", "\n", $html); + } if ($config->get('HTML.Trusted')) { // escape convoluted CDATA @@ -263,6 +307,8 @@ class HTMLPurifier_Lexer // escape CDATA $html = $this->escapeCDATA($html); + $html = $this->removeIEConditional($html); + // extract body from document if applicable if ($config->get('Core.ConvertDocumentToFragment')) { $e = false; @@ -284,6 +330,11 @@ class HTMLPurifier_Lexer // represent non-SGML characters (horror, horror!) $html = HTMLPurifier_Encoder::cleanUTF8($html); + // if processing instructions are to removed, remove them now + if ($config->get('Core.RemoveProcessingInstructions')) { + $html = preg_replace('#<\?.+?\?>#s', '', $html); + } + return $html; } @@ -291,7 +342,8 @@ class HTMLPurifier_Lexer * Takes a string of HTML (fragment or document) and returns the content * @todo Consider making protected */ - public function extractBody($html) { + public function extractBody($html) + { $matches = array(); $result = preg_match('!<body[^>]*>(.*)</body>!is', $html, $matches); if ($result) { @@ -300,7 +352,6 @@ class HTMLPurifier_Lexer return $html; } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Lexer/DOMLex.php b/library/HTMLPurifier/Lexer/DOMLex.php index 20dc2ed48..720754454 100644 --- a/library/HTMLPurifier/Lexer/DOMLex.php +++ b/library/HTMLPurifier/Lexer/DOMLex.php @@ -27,16 +27,26 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer { + /** + * @type HTMLPurifier_TokenFactory + */ private $factory; - public function __construct() { + public function __construct() + { // setup the factory parent::__construct(); $this->factory = new HTMLPurifier_TokenFactory(); } - public function tokenizeHTML($html, $config, $context) { - + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] + */ + public function tokenizeHTML($html, $config, $context) + { $html = $this->normalize($html, $config, $context); // attempt to armor stray angled brackets that cannot possibly @@ -65,30 +75,67 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer $tokens = array(); $this->tokenizeDOM( $doc->getElementsByTagName('html')->item(0)-> // <html> - getElementsByTagName('body')->item(0)-> // <body> - getElementsByTagName('div')->item(0) // <div> - , $tokens); + getElementsByTagName('body')->item(0)-> // <body> + getElementsByTagName('div')->item(0), // <div> + $tokens + ); return $tokens; } /** - * Recursive function that tokenizes a node, putting it into an accumulator. - * - * @param $node DOMNode to be tokenized. - * @param $tokens Array-list of already tokenized tokens. - * @param $collect Says whether or start and close are collected, set to - * false at first recursion because it's the implicit DIV - * tag you're dealing with. - * @returns Tokens of node appended to previously passed tokens. + * Iterative function that tokenizes a node, putting it into an accumulator. + * To iterate is human, to recurse divine - L. Peter Deutsch + * @param DOMNode $node DOMNode to be tokenized. + * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. + * @return HTMLPurifier_Token of node appended to previously passed tokens. */ - protected function tokenizeDOM($node, &$tokens, $collect = false) { + protected function tokenizeDOM($node, &$tokens) + { + $level = 0; + $nodes = array($level => new HTMLPurifier_Queue(array($node))); + $closingNodes = array(); + do { + while (!$nodes[$level]->isEmpty()) { + $node = $nodes[$level]->shift(); // FIFO + $collect = $level > 0 ? true : false; + $needEndingTag = $this->createStartNode($node, $tokens, $collect); + if ($needEndingTag) { + $closingNodes[$level][] = $node; + } + if ($node->childNodes && $node->childNodes->length) { + $level++; + $nodes[$level] = new HTMLPurifier_Queue(); + foreach ($node->childNodes as $childNode) { + $nodes[$level]->push($childNode); + } + } + } + $level--; + if ($level && isset($closingNodes[$level])) { + while ($node = array_pop($closingNodes[$level])) { + $this->createEndNode($node, $tokens); + } + } + } while ($level > 0); + } + /** + * @param DOMNode $node DOMNode to be tokenized. + * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. + * @param bool $collect Says whether or start and close are collected, set to + * false at first recursion because it's the implicit DIV + * tag you're dealing with. + * @return bool if the token needs an endtoken + * @todo data and tagName properties don't seem to exist in DOMNode? + */ + protected function createStartNode($node, &$tokens, $collect) + { // intercept non element nodes. WE MUST catch all of them, // but we're not getting the character reference nodes because // those should have been preprocessed if ($node->nodeType === XML_TEXT_NODE) { $tokens[] = $this->factory->createText($node->data); - return; + return false; } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) { // undo libxml's special treatment of <script> and <style> tags $last = end($tokens); @@ -106,59 +153,61 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer } } $tokens[] = $this->factory->createText($this->parseData($data)); - return; + return false; } elseif ($node->nodeType === XML_COMMENT_NODE) { // this is code is only invoked for comments in script/style in versions // of libxml pre-2.6.28 (regular comments, of course, are still // handled regularly) $tokens[] = $this->factory->createComment($node->data); - return; - } elseif ( + return false; + } elseif ($node->nodeType !== XML_ELEMENT_NODE) { // not-well tested: there may be other nodes we have to grab - $node->nodeType !== XML_ELEMENT_NODE - ) { - return; + return false; } - $attr = $node->hasAttributes() ? - $this->transformAttrToAssoc($node->attributes) : - array(); + $attr = $node->hasAttributes() ? $this->transformAttrToAssoc($node->attributes) : array(); // We still have to make sure that the element actually IS empty if (!$node->childNodes->length) { if ($collect) { $tokens[] = $this->factory->createEmpty($node->tagName, $attr); } + return false; } else { - if ($collect) { // don't wrap on first iteration + if ($collect) { $tokens[] = $this->factory->createStart( $tag_name = $node->tagName, // somehow, it get's dropped $attr ); } - foreach ($node->childNodes as $node) { - // remember, it's an accumulator. Otherwise, we'd have - // to use array_merge - $this->tokenizeDOM($node, $tokens, true); - } - if ($collect) { - $tokens[] = $this->factory->createEnd($tag_name); - } + return true; } + } + /** + * @param DOMNode $node + * @param HTMLPurifier_Token[] $tokens + */ + protected function createEndNode($node, &$tokens) + { + $tokens[] = $this->factory->createEnd($node->tagName); } + /** * Converts a DOMNamedNodeMap of DOMAttr objects into an assoc array. * - * @param $attribute_list DOMNamedNodeMap of DOMAttr objects. - * @returns Associative array of attributes. + * @param DOMNamedNodeMap $node_map DOMNamedNodeMap of DOMAttr objects. + * @return array Associative array of attributes. */ - protected function transformAttrToAssoc($node_map) { + protected function transformAttrToAssoc($node_map) + { // NamedNodeMap is documented very well, so we're using undocumented // features, namely, the fact that it implements Iterator and // has a ->length attribute - if ($node_map->length === 0) return array(); + if ($node_map->length === 0) { + return array(); + } $array = array(); foreach ($node_map as $attr) { $array[$attr->name] = $attr->value; @@ -168,46 +217,64 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer /** * An error handler that mutes all errors + * @param int $errno + * @param string $errstr */ - public function muteErrorHandler($errno, $errstr) {} + public function muteErrorHandler($errno, $errstr) + { + } /** * Callback function for undoing escaping of stray angled brackets * in comments + * @param array $matches + * @return string */ - public function callbackUndoCommentSubst($matches) { - return '<!--' . strtr($matches[1], array('&'=>'&','<'=>'<')) . $matches[2]; + public function callbackUndoCommentSubst($matches) + { + return '<!--' . strtr($matches[1], array('&' => '&', '<' => '<')) . $matches[2]; } /** * Callback function that entity-izes ampersands in comments so that * callbackUndoCommentSubst doesn't clobber them + * @param array $matches + * @return string */ - public function callbackArmorCommentEntities($matches) { + public function callbackArmorCommentEntities($matches) + { return '<!--' . str_replace('&', '&', $matches[1]) . $matches[2]; } /** * Wraps an HTML fragment in the necessary HTML + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string */ - protected function wrapHTML($html, $config, $context) { + protected function wrapHTML($html, $config, $context) + { $def = $config->getDefinition('HTML'); $ret = ''; if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) { $ret .= '<!DOCTYPE html '; - if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" '; - if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" '; + if (!empty($def->doctype->dtdPublic)) { + $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" '; + } + if (!empty($def->doctype->dtdSystem)) { + $ret .= '"' . $def->doctype->dtdSystem . '" '; + } $ret .= '>'; } $ret .= '<html><head>'; $ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />'; // No protection if $html contains a stray </div>! - $ret .= '</head><body><div>'.$html.'</div></body></html>'; + $ret .= '</head><body><div>' . $html . '</div></body></html>'; return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Lexer/DirectLex.php b/library/HTMLPurifier/Lexer/DirectLex.php index 456e6e190..746b6e315 100644 --- a/library/HTMLPurifier/Lexer/DirectLex.php +++ b/library/HTMLPurifier/Lexer/DirectLex.php @@ -12,30 +12,44 @@ */ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer { - + /** + * @type bool + */ public $tracksLineNumbers = true; /** * Whitespace characters for str(c)spn. + * @type string */ protected $_whitespace = "\x20\x09\x0D\x0A"; /** * Callback function for script CDATA fudge - * @param $matches, in form of array(opening tag, contents, closing tag) + * @param array $matches, in form of array(opening tag, contents, closing tag) + * @return string */ - protected function scriptCallback($matches) { + protected function scriptCallback($matches) + { return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8') . $matches[3]; } - public function tokenizeHTML($html, $config, $context) { - + /** + * @param String $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array|HTMLPurifier_Token[] + */ + public function tokenizeHTML($html, $config, $context) + { // special normalization for script tags without any armor // our "armor" heurstic is a < sign any number of whitespaces after // the first script tag if ($config->get('HTML.Trusted')) { - $html = preg_replace_callback('#(<script[^>]*>)(\s*[^<].+?)(</script>)#si', - array($this, 'scriptCallback'), $html); + $html = preg_replace_callback( + '#(<script[^>]*>)(\s*[^<].+?)(</script>)#si', + array($this, 'scriptCallback'), + $html + ); } $html = $this->normalize($html, $config, $context); @@ -55,15 +69,15 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer if ($maintain_line_numbers) { $current_line = 1; - $current_col = 0; + $current_col = 0; $length = strlen($html); } else { $current_line = false; - $current_col = false; + $current_col = false; $length = false; } $context->register('CurrentLine', $current_line); - $context->register('CurrentCol', $current_col); + $context->register('CurrentCol', $current_col); $nl = "\n"; // how often to manually recalculate. This will ALWAYS be right, // but it's pretty wasteful. Set to 0 to turn off @@ -77,16 +91,14 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer // for testing synchronization $loops = 0; - while(++$loops) { - + while (++$loops) { // $cursor is either at the start of a token, or inside of // a tag (i.e. there was a < immediately before it), as indicated // by $inside_tag if ($maintain_line_numbers) { - // $rcursor, however, is always at the start of a token. - $rcursor = $cursor - (int) $inside_tag; + $rcursor = $cursor - (int)$inside_tag; // Column number is cheap, so we calculate it every round. // We're interested at the *end* of the newline string, so @@ -96,14 +108,11 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer $current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1); // recalculate lines - if ( - $synchronize_interval && // synchronization is on - $cursor > 0 && // cursor is further than zero - $loops % $synchronize_interval === 0 // time to synchronize! - ) { + if ($synchronize_interval && // synchronization is on + $cursor > 0 && // cursor is further than zero + $loops % $synchronize_interval === 0) { // time to synchronize! $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor); } - } $position_next_lt = strpos($html, '<', $cursor); @@ -119,35 +128,42 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer if (!$inside_tag && $position_next_lt !== false) { // We are not inside tag and there still is another tag to parse $token = new - HTMLPurifier_Token_Text( - $this->parseData( - substr( - $html, $cursor, $position_next_lt - $cursor - ) + HTMLPurifier_Token_Text( + $this->parseData( + substr( + $html, + $cursor, + $position_next_lt - $cursor ) - ); + ) + ); if ($maintain_line_numbers) { $token->rawPosition($current_line, $current_col); $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor); } $array[] = $token; - $cursor = $position_next_lt + 1; + $cursor = $position_next_lt + 1; $inside_tag = true; continue; } elseif (!$inside_tag) { // We are not inside tag but there are no more tags // If we're already at the end, break - if ($cursor === strlen($html)) break; + if ($cursor === strlen($html)) { + break; + } // Create Text of rest of string $token = new - HTMLPurifier_Token_Text( - $this->parseData( - substr( - $html, $cursor - ) + HTMLPurifier_Token_Text( + $this->parseData( + substr( + $html, + $cursor ) - ); - if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col); + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } $array[] = $token; break; } elseif ($inside_tag && $position_next_gt !== false) { @@ -171,16 +187,16 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer } // Check if it's a comment - if ( - substr($segment, 0, 3) === '!--' - ) { + if (substr($segment, 0, 3) === '!--') { // re-determine segment length, looking for --> $position_comment_end = strpos($html, '-->', $cursor); if ($position_comment_end === false) { // uh oh, we have a comment that extends to // infinity. Can't be helped: set comment // end position to end of string - if ($e) $e->send(E_WARNING, 'Lexer: Unclosed comment'); + if ($e) { + $e->send(E_WARNING, 'Lexer: Unclosed comment'); + } $position_comment_end = strlen($html); $end = true; } else { @@ -189,11 +205,13 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer $strlen_segment = $position_comment_end - $cursor; $segment = substr($html, $cursor, $strlen_segment); $token = new - HTMLPurifier_Token_Comment( - substr( - $segment, 3, $strlen_segment - 3 - ) - ); + HTMLPurifier_Token_Comment( + substr( + $segment, + 3, + $strlen_segment - 3 + ) + ); if ($maintain_line_numbers) { $token->rawPosition($current_line, $current_col); $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment); @@ -205,7 +223,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer } // Check if it's an end tag - $is_end_tag = (strpos($segment,'/') === 0); + $is_end_tag = (strpos($segment, '/') === 0); if ($is_end_tag) { $type = substr($segment, 1); $token = new HTMLPurifier_Token_End($type); @@ -224,7 +242,9 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer // text and go our merry way if (!ctype_alpha($segment[0])) { // XML: $segment[0] !== '_' && $segment[0] !== ':' - if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt'); + if ($e) { + $e->send(E_NOTICE, 'Lexer: Unescaped lt'); + } $token = new HTMLPurifier_Token_Text('<'); if ($maintain_line_numbers) { $token->rawPosition($current_line, $current_col); @@ -239,7 +259,7 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer // trailing slash. Remember, we could have a tag like <br>, so // any later token processing scripts must convert improperly // classified EmptyTags from StartTags. - $is_self_closing = (strrpos($segment,'/') === $strlen_segment-1); + $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1); if ($is_self_closing) { $strlen_segment--; $segment = substr($segment, 0, $strlen_segment); @@ -269,14 +289,16 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer $attribute_string = trim( substr( - $segment, $position_first_space + $segment, + $position_first_space ) ); if ($attribute_string) { $attr = $this->parseAttributeString( - $attribute_string - , $config, $context - ); + $attribute_string, + $config, + $context + ); } else { $attr = array(); } @@ -296,15 +318,19 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer continue; } else { // inside tag, but there's no ending > sign - if ($e) $e->send(E_WARNING, 'Lexer: Missing gt'); + if ($e) { + $e->send(E_WARNING, 'Lexer: Missing gt'); + } $token = new - HTMLPurifier_Token_Text( - '<' . - $this->parseData( - substr($html, $cursor) - ) - ); - if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col); + HTMLPurifier_Token_Text( + '<' . + $this->parseData( + substr($html, $cursor) + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } // no cursor scroll? Hmm... $array[] = $token; break; @@ -319,8 +345,14 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer /** * PHP 5.0.x compatible substr_count that implements offset and length + * @param string $haystack + * @param string $needle + * @param int $offset + * @param int $length + * @return int */ - protected function substrCount($haystack, $needle, $offset, $length) { + protected function substrCount($haystack, $needle, $offset, $length) + { static $oldVersion; if ($oldVersion === null) { $oldVersion = version_compare(PHP_VERSION, '5.1', '<'); @@ -336,13 +368,18 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer /** * Takes the inside of an HTML tag and makes an assoc array of attributes. * - * @param $string Inside of tag excluding name. - * @returns Assoc array of attributes. + * @param string $string Inside of tag excluding name. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array Assoc array of attributes. */ - public function parseAttributeString($string, $config, $context) { - $string = (string) $string; // quick typecast + public function parseAttributeString($string, $config, $context) + { + $string = (string)$string; // quick typecast - if ($string == '') return array(); // no attributes + if ($string == '') { + return array(); + } // no attributes $e = false; if ($config->get('Core.CollectErrors')) { @@ -361,46 +398,55 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer list($key, $quoted_value) = explode('=', $string); $quoted_value = trim($quoted_value); if (!$key) { - if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key'); + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } return array(); } - if (!$quoted_value) return array($key => ''); + if (!$quoted_value) { + return array($key => ''); + } $first_char = @$quoted_value[0]; - $last_char = @$quoted_value[strlen($quoted_value)-1]; + $last_char = @$quoted_value[strlen($quoted_value) - 1]; $same_quote = ($first_char == $last_char); $open_quote = ($first_char == '"' || $first_char == "'"); - if ( $same_quote && $open_quote) { + if ($same_quote && $open_quote) { // well behaved $value = substr($quoted_value, 1, strlen($quoted_value) - 2); } else { // not well behaved if ($open_quote) { - if ($e) $e->send(E_ERROR, 'Lexer: Missing end quote'); + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing end quote'); + } $value = substr($quoted_value, 1); } else { $value = $quoted_value; } } - if ($value === false) $value = ''; + if ($value === false) { + $value = ''; + } return array($key => $this->parseData($value)); } // setup loop environment - $array = array(); // return assoc array of attributes + $array = array(); // return assoc array of attributes $cursor = 0; // current position in string (moves forward) - $size = strlen($string); // size of the string (stays the same) + $size = strlen($string); // size of the string (stays the same) // if we have unquoted attributes, the parser expects a terminating // space, so let's guarantee that there's always a terminating space. $string .= ' '; - while(true) { - - if ($cursor >= $size) { - break; + $old_cursor = -1; + while ($cursor < $size) { + if ($old_cursor >= $cursor) { + throw new Exception("Infinite loop detected"); } + $old_cursor = $cursor; $cursor += ($value = strspn($string, $this->_whitespace, $cursor)); // grab the key @@ -415,8 +461,10 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer $key = substr($string, $key_begin, $key_end - $key_begin); if (!$key) { - if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key'); - $cursor += strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + $cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop continue; // empty key } @@ -467,24 +515,25 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer } $value = substr($string, $value_begin, $value_end - $value_begin); - if ($value === false) $value = ''; + if ($value === false) { + $value = ''; + } $array[$key] = $this->parseData($value); $cursor++; - } else { // boolattr if ($key !== '') { $array[$key] = $key; } else { // purely theoretical - if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key'); + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } } - } } return $array; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Lexer/PEARSax3.php b/library/HTMLPurifier/Lexer/PEARSax3.php deleted file mode 100644 index 1d358c7b6..000000000 --- a/library/HTMLPurifier/Lexer/PEARSax3.php +++ /dev/null @@ -1,139 +0,0 @@ -<?php - -/** - * Proof-of-concept lexer that uses the PEAR package XML_HTMLSax3 to parse HTML. - * - * PEAR, not suprisingly, also has a SAX parser for HTML. I don't know - * very much about implementation, but it's fairly well written. However, that - * abstraction comes at a price: performance. You need to have it installed, - * and if the API changes, it might break our adapter. Not sure whether or not - * it's UTF-8 aware, but it has some entity parsing trouble (in all areas, - * text and attributes). - * - * Quite personally, I don't recommend using the PEAR class, and the defaults - * don't use it. The unit tests do perform the tests on the SAX parser too, but - * whatever it does for poorly formed HTML is up to it. - * - * @todo Generalize so that XML_HTMLSax is also supported. - * - * @warning Entity-resolution inside attributes is broken. - */ - -class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer -{ - - /** - * Internal accumulator array for SAX parsers. - */ - protected $tokens = array(); - protected $last_token_was_empty; - - private $parent_handler; - private $stack = array(); - - public function tokenizeHTML($string, $config, $context) { - - $this->tokens = array(); - $this->last_token_was_empty = false; - - $string = $this->normalize($string, $config, $context); - - $this->parent_handler = set_error_handler(array($this, 'muteStrictErrorHandler')); - - $parser = new XML_HTMLSax3(); - $parser->set_object($this); - $parser->set_element_handler('openHandler','closeHandler'); - $parser->set_data_handler('dataHandler'); - $parser->set_escape_handler('escapeHandler'); - - // doesn't seem to work correctly for attributes - $parser->set_option('XML_OPTION_ENTITIES_PARSED', 1); - - $parser->parse($string); - - restore_error_handler(); - - return $this->tokens; - - } - - /** - * Open tag event handler, interface is defined by PEAR package. - */ - public function openHandler(&$parser, $name, $attrs, $closed) { - // entities are not resolved in attrs - foreach ($attrs as $key => $attr) { - $attrs[$key] = $this->parseData($attr); - } - if ($closed) { - $this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs); - $this->last_token_was_empty = true; - } else { - $this->tokens[] = new HTMLPurifier_Token_Start($name, $attrs); - } - $this->stack[] = $name; - return true; - } - - /** - * Close tag event handler, interface is defined by PEAR package. - */ - public function closeHandler(&$parser, $name) { - // HTMLSax3 seems to always send empty tags an extra close tag - // check and ignore if you see it: - // [TESTME] to make sure it doesn't overreach - if ($this->last_token_was_empty) { - $this->last_token_was_empty = false; - return true; - } - $this->tokens[] = new HTMLPurifier_Token_End($name); - if (!empty($this->stack)) array_pop($this->stack); - return true; - } - - /** - * Data event handler, interface is defined by PEAR package. - */ - public function dataHandler(&$parser, $data) { - $this->last_token_was_empty = false; - $this->tokens[] = new HTMLPurifier_Token_Text($data); - return true; - } - - /** - * Escaped text handler, interface is defined by PEAR package. - */ - public function escapeHandler(&$parser, $data) { - if (strpos($data, '--') === 0) { - // remove trailing and leading double-dashes - $data = substr($data, 2); - if (strlen($data) >= 2 && substr($data, -2) == "--") { - $data = substr($data, 0, -2); - } - if (isset($this->stack[sizeof($this->stack) - 1]) && - $this->stack[sizeof($this->stack) - 1] == "style") { - $this->tokens[] = new HTMLPurifier_Token_Text($data); - } else { - $this->tokens[] = new HTMLPurifier_Token_Comment($data); - } - $this->last_token_was_empty = false; - } - // CDATA is handled elsewhere, but if it was handled here: - //if (strpos($data, '[CDATA[') === 0) { - // $this->tokens[] = new HTMLPurifier_Token_Text( - // substr($data, 7, strlen($data) - 9) ); - //} - return true; - } - - /** - * An error handler that mutes strict errors - */ - public function muteStrictErrorHandler($errno, $errstr, $errfile=null, $errline=null, $errcontext=null) { - if ($errno == E_STRICT) return; - return call_user_func($this->parent_handler, $errno, $errstr, $errfile, $errline, $errcontext); - } - -} - -// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Lexer/PH5P.php b/library/HTMLPurifier/Lexer/PH5P.php index fa1bf973e..a4587e4cd 100644 --- a/library/HTMLPurifier/Lexer/PH5P.php +++ b/library/HTMLPurifier/Lexer/PH5P.php @@ -3,16 +3,23 @@ /** * Experimental HTML5-based parser using Jeroen van der Meer's PH5P library. * Occupies space in the HTML5 pseudo-namespace, which may cause conflicts. - * + * * @note * Recent changes to PHP's DOM extension have resulted in some fatal * error conditions with the original version of PH5P. Pending changes, - * this lexer will punt to DirectLex if DOM throughs an exception. + * this lexer will punt to DirectLex if DOM throws an exception. */ -class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex { - - public function tokenizeHTML($html, $config, $context) { +class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex +{ + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] + */ + public function tokenizeHTML($html, $config, $context) + { $new_html = $this->normalize($html, $config, $context); $new_html = $this->wrapHTML($new_html, $config, $context); try { @@ -27,40 +34,42 @@ class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex { $tokens = array(); $this->tokenizeDOM( $doc->getElementsByTagName('html')->item(0)-> // <html> - getElementsByTagName('body')->item(0)-> // <body> - getElementsByTagName('div')->item(0) // <div> - , $tokens); + getElementsByTagName('body')->item(0)-> // <body> + getElementsByTagName('div')->item(0) // <div> + , + $tokens + ); return $tokens; } - } /* -Copyright 2007 Jeroen van der Meer <http://jero.net/> +Copyright 2007 Jeroen van der Meer <http://jero.net/> -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: +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 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. +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 { +class HTML5 +{ private $data; private $char; private $EOF; @@ -69,91 +78,418 @@ class HTML5 { 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; + 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 DOCTYPE = 0; const STARTTAG = 1; - const ENDTAG = 2; - const COMMENT = 3; + 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, $data); + const EOF = 5; + public function __construct($data) + { $this->data = $data; $this->char = -1; - $this->EOF = strlen($data); + $this->EOF = strlen($data); $this->tree = new HTML5TreeConstructer; $this->content_model = self::PCDATA; $this->state = 'data'; - while($this->state !== null) { - $this->{$this->state.'State'}(); + while ($this->state !== null) { + $this->{$this->state . 'State'}(); } } - public function save() { + public function save() + { return $this->tree->save(); } - private function char() { + private function char() + { return ($this->char < $this->EOF) ? $this->data[$this->char] : false; } - private function character($s, $l = 0) { - if($s + $l < $this->EOF) { - if($l === 0) { + private function character($s, $l = 0) + { + if ($s + $l < $this->EOF) { + if ($l === 0) { return $this->data[$s]; } else { return substr($this->data, $s, $l); @@ -161,46 +497,52 @@ class HTML5 { } } - private function characters($char_class, $start) { - return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start)); + private function characters($char_class, $start) + { + return preg_replace('#^([' . $char_class . ']+).*#s', '\\1', substr($this->data, $start)); } - private function dataState() { + private function dataState() + { // Consume the next input character $this->char++; $char = $this->char(); - if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { + if ($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 === '-') { + } elseif ($char === '-') { /* If the content model flag is set to either the RCDATA state or the CDATA state, and the escape flag is false, and there are at least three characters before this one in the input stream, and the last four characters in the input stream, including this one, are U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS, and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */ - if(($this->content_model === self::RCDATA || $this->content_model === - self::CDATA) && $this->escape === false && - $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') { + if (($this->content_model === self::RCDATA || $this->content_model === + self::CDATA) && $this->escape === false && + $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--' + ) { $this->escape = true; } /* In any case, emit the input character as a character token. Stay in the data state. */ - $this->emitToken(array( - 'type' => self::CHARACTR, - 'data' => $char - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); - /* U+003C LESS-THAN SIGN (<) */ - } elseif($char === '<' && ($this->content_model === self::PCDATA || - (($this->content_model === self::RCDATA || - $this->content_model === self::CDATA) && $this->escape === false))) { + /* U+003C LESS-THAN SIGN (<) */ + } elseif ($char === '<' && ($this->content_model === self::PCDATA || + (($this->content_model === self::RCDATA || + $this->content_model === self::CDATA) && $this->escape === false)) + ) { /* When the content model flag is set to the PCDATA state: switch to the tag open state. @@ -211,39 +553,44 @@ class HTML5 { Otherwise: treat it as per the "anything else" entry below. */ $this->state = 'tagOpen'; - /* U+003E GREATER-THAN SIGN (>) */ - } elseif($char === '>') { + /* U+003E GREATER-THAN SIGN (>) */ + } elseif ($char === '>') { /* If the content model flag is set to either the RCDATA state or the CDATA state, and the escape flag is true, and the last three characters in the input stream including this one are U+002D HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"), set the escape flag to false. */ - if(($this->content_model === self::RCDATA || - $this->content_model === self::CDATA) && $this->escape === true && - $this->character($this->char, 3) === '-->') { + 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 - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Emit an end-of-file token. */ $this->EOF(); - } elseif($this->content_model === self::PLAINTEXT) { + } 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) - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => substr($this->data, $this->char) + ) + ); $this->EOF(); @@ -252,37 +599,43 @@ class HTML5 { 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); + $len = strcspn($this->data, '<&', $this->char); $char = substr($this->data, $this->char, $len); $this->char += $len - 1; - $this->emitToken(array( - 'type' => self::CHARACTR, - 'data' => $char - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); $this->state = 'data'; } } - private function entityDataState() { + 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 - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); // Finally, switch to the data state. $this->state = 'data'; } - private function tagOpenState() { - switch($this->content_model) { + private function tagOpenState() + { + switch ($this->content_model) { case self::RCDATA: case self::CDATA: /* If the next input character is a U+002F SOLIDUS (/) character, @@ -290,19 +643,21 @@ class HTML5 { input character is not a U+002F SOLIDUS (/) character, emit a U+003C LESS-THAN SIGN character token and switch to the data state to process the next input character. */ - if($this->character($this->char + 1) === '/') { + if ($this->character($this->char + 1) === '/') { $this->char++; $this->state = 'closeTagOpen'; } else { - $this->emitToken(array( - 'type' => self::CHARACTR, - 'data' => '<' - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<' + ) + ); $this->state = 'data'; } - break; + break; case self::PCDATA: // If the content model flag is set to the PCDATA state @@ -310,42 +665,44 @@ class HTML5 { $this->char++; $char = $this->char(); - if($char === '!') { + if ($char === '!') { /* U+0021 EXCLAMATION MARK (!) Switch to the markup declaration open state. */ $this->state = 'markupDeclarationOpen'; - } elseif($char === '/') { + } elseif ($char === '/') { /* U+002F SOLIDUS (/) Switch to the close tag open state. */ $this->state = 'closeTagOpen'; - } elseif(preg_match('/^[A-Za-z]$/', $char)) { + } elseif (preg_match('/^[A-Za-z]$/', $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() + 'name' => strtolower($char), + 'type' => self::STARTTAG, + 'attr' => array() ); $this->state = 'tagName'; - } elseif($char === '>') { + } 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->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<>' + ) + ); $this->state = 'data'; - } elseif($char === '?') { + } elseif ($char === '?') { /* U+003F QUESTION MARK (?) Parse error. Switch to the bogus comment state. */ $this->state = 'bogusComment'; @@ -354,25 +711,31 @@ class HTML5 { /* 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->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<' + ) + ); $this->char--; $this->state = 'data'; } - break; + break; } } - private function closeTagOpenState() { + 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 === $this->char)))) { + if (($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 @@ -388,10 +751,12 @@ class HTML5 { ...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' => '</' - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '</' + ) + ); $this->state = 'data'; @@ -402,32 +767,34 @@ class HTML5 { $this->char++; $char = $this->char(); - if(preg_match('/^[A-Za-z]$/', $char)) { + if (preg_match('/^[A-Za-z]$/', $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 + 'name' => strtolower($char), + 'type' => self::ENDTAG ); $this->state = 'tagName'; - } elseif($char === '>') { + } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Parse error. Switch to the data state. */ $this->state = 'data'; - } elseif($this->char === $this->EOF) { + } elseif ($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' => '</' - )); + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '</' + ) + ); $this->char--; $this->state = 'data'; @@ -439,12 +806,13 @@ class HTML5 { } } - private function tagNameState() { + private function tagNameState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000B LINE TABULATION @@ -453,13 +821,13 @@ class HTML5 { Switch to the before attribute name state. */ $this->state = 'beforeAttributeName'; - } elseif($char === '>') { + } 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 === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Parse error. Emit the current tag token. Reconsume the EOF character in the data state. */ @@ -468,7 +836,7 @@ class HTML5 { $this->char--; $this->state = 'data'; - } elseif($char === '/') { + } elseif ($char === '/') { /* U+002F SOLIDUS (/) Parse error unless this is a permitted slash. Switch to the before attribute name state. */ @@ -483,12 +851,13 @@ class HTML5 { } } - private function beforeAttributeNameState() { + private function beforeAttributeNameState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000B LINE TABULATION @@ -497,19 +866,19 @@ class HTML5 { Stay in the before attribute name state. */ $this->state = 'beforeAttributeName'; - } elseif($char === '>') { + } 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 === '/') { + } 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 === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Parse error. Emit the current tag token. Reconsume the EOF character in the data state. */ @@ -524,7 +893,7 @@ class HTML5 { 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), + 'name' => strtolower($char), 'value' => null ); @@ -532,12 +901,13 @@ class HTML5 { } } - private function attributeNameState() { + private function attributeNameState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000B LINE TABULATION @@ -546,24 +916,24 @@ class HTML5 { Stay in the before attribute name state. */ $this->state = 'afterAttributeName'; - } elseif($char === '=') { + } elseif ($char === '=') { /* U+003D EQUALS SIGN (=) Switch to the before attribute value state. */ $this->state = 'beforeAttributeValue'; - } elseif($char === '>') { + } 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) !== '>') { + } 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 === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Parse error. Emit the current tag token. Reconsume the EOF character in the data state. */ @@ -583,12 +953,13 @@ class HTML5 { } } - private function afterAttributeNameState() { + private function afterAttributeNameState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000B LINE TABULATION @@ -597,24 +968,24 @@ class HTML5 { Stay in the after attribute name state. */ $this->state = 'afterAttributeName'; - } elseif($char === '=') { + } elseif ($char === '=') { /* U+003D EQUALS SIGN (=) Switch to the before attribute value state. */ $this->state = 'beforeAttributeValue'; - } elseif($char === '>') { + } 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) !== '>') { + } 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 === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Parse error. Emit the current tag token. Reconsume the EOF character in the data state. */ @@ -629,7 +1000,7 @@ class HTML5 { 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), + 'name' => strtolower($char), 'value' => null ); @@ -637,12 +1008,13 @@ class HTML5 { } } - private function beforeAttributeValueState() { + private function beforeAttributeValueState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000B LINE TABULATION @@ -651,24 +1023,24 @@ class HTML5 { Stay in the before attribute value state. */ $this->state = 'beforeAttributeValue'; - } elseif($char === '"') { + } elseif ($char === '"') { /* U+0022 QUOTATION MARK (") Switch to the attribute value (double-quoted) state. */ $this->state = 'attributeValueDoubleQuoted'; - } elseif($char === '&') { + } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the attribute value (unquoted) state and reconsume this input character. */ $this->char--; $this->state = 'attributeValueUnquoted'; - } elseif($char === '\'') { + } elseif ($char === '\'') { /* U+0027 APOSTROPHE (') Switch to the attribute value (single-quoted) state. */ $this->state = 'attributeValueSingleQuoted'; - } elseif($char === '>') { + } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); @@ -685,22 +1057,23 @@ class HTML5 { } } - private function attributeValueDoubleQuotedState() { + private function attributeValueDoubleQuotedState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if($char === '"') { + if ($char === '"') { /* U+0022 QUOTATION MARK (") Switch to the before attribute name state. */ $this->state = 'beforeAttributeName'; - } elseif($char === '&') { + } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the entity in attribute value state. */ $this->entityInAttributeValueState('double'); - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Parse error. Emit the current tag token. Reconsume the character in the data state. */ @@ -720,22 +1093,23 @@ class HTML5 { } } - private function attributeValueSingleQuotedState() { + private function attributeValueSingleQuotedState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if($char === '\'') { + if ($char === '\'') { /* U+0022 QUOTATION MARK (') Switch to the before attribute name state. */ $this->state = 'beforeAttributeName'; - } elseif($char === '&') { + } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the entity in attribute value state. */ $this->entityInAttributeValueState('single'); - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { /* EOF Parse error. Emit the current tag token. Reconsume the character in the data state. */ @@ -755,12 +1129,13 @@ class HTML5 { } } - private function attributeValueUnquotedState() { + private function attributeValueUnquotedState() + { // Consume the next input character: $this->char++; $char = $this->character($this->char); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { /* U+0009 CHARACTER TABULATION U+000A LINE FEED (LF) U+000B LINE TABULATION @@ -769,12 +1144,12 @@ class HTML5 { Switch to the before attribute name state. */ $this->state = 'beforeAttributeName'; - } elseif($char === '&') { + } elseif ($char === '&') { /* U+0026 AMPERSAND (&) Switch to the entity in attribute value state. */ $this->entityInAttributeValueState(); - } elseif($char === '>') { + } elseif ($char === '>') { /* U+003E GREATER-THAN SIGN (>) Emit the current tag token. Switch to the data state. */ $this->emitToken($this->token); @@ -791,7 +1166,8 @@ class HTML5 { } } - private function entityInAttributeValueState() { + private function entityInAttributeValueState() + { // Attempt to consume an entity. $entity = $this->entity(); @@ -806,7 +1182,8 @@ class HTML5 { $this->token['attr'][$last]['value'] .= $char; } - private function bogusCommentState() { + 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 @@ -816,10 +1193,12 @@ class HTML5 { 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->emitToken( + array( + 'data' => $data, + 'type' => self::COMMENT + ) + ); $this->char += strlen($data); @@ -827,16 +1206,17 @@ class HTML5 { $this->state = 'data'; /* If the end of the file was reached, reconsume the EOF character. */ - if($this->char === $this->EOF) { + if ($this->char === $this->EOF) { $this->char = $this->EOF - 1; } } - private function markupDeclarationOpenState() { + private function markupDeclarationOpenState() + { /* If the next two characters are both U+002D HYPHEN-MINUS (-) characters, consume those two characters, create a comment token whose data is the empty string, and switch to the comment state. */ - if($this->character($this->char + 1, 2) === '--') { + if ($this->character($this->char + 1, 2) === '--') { $this->char += 2; $this->state = 'comment'; $this->token = array( @@ -844,41 +1224,42 @@ class HTML5 { 'type' => self::COMMENT ); - /* Otherwise if the next seven chacacters are a case-insensitive match - for the word "DOCTYPE", then consume those characters and switch to the - DOCTYPE state. */ - } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') { + /* Otherwise if the next seven chacacters are a case-insensitive match + for the word "DOCTYPE", then consume those characters and switch to the + DOCTYPE state. */ + } elseif (strtolower($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. */ + /* 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() { + private function commentState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); /* U+002D HYPHEN-MINUS (-) */ - if($char === '-') { + if ($char === '-') { /* Switch to the comment dash state */ $this->state = 'commentDash'; - /* EOF */ - } elseif($this->char === $this->EOF) { + /* EOF */ + } elseif ($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 */ + /* Anything else */ } else { /* Append the input character to the comment token's data. Stay in the comment state. */ @@ -886,62 +1267,65 @@ class HTML5 { } } - private function commentDashState() { + private function commentDashState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); /* U+002D HYPHEN-MINUS (-) */ - if($char === '-') { + if ($char === '-') { /* Switch to the comment end state */ $this->state = 'commentEnd'; - /* EOF */ - } elseif($this->char === $this->EOF) { + /* EOF */ + } elseif ($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 */ + /* 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->token['data'] .= '-' . $char; $this->state = 'comment'; } } - private function commentEndState() { + private function commentEndState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); - if($char === '>') { + if ($char === '>') { $this->emitToken($this->token); $this->state = 'data'; - } elseif($char === '-') { + } elseif ($char === '-') { $this->token['data'] .= '-'; - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { $this->emitToken($this->token); $this->char--; $this->state = 'data'; } else { - $this->token['data'] .= '--'.$char; + $this->token['data'] .= '--' . $char; $this->state = 'comment'; } } - private function doctypeState() { + private function doctypeState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { $this->state = 'beforeDoctypeName'; } else { @@ -950,15 +1334,16 @@ class HTML5 { } } - private function beforeDoctypeNameState() { + private function beforeDoctypeNameState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { // Stay in the before DOCTYPE name state. - } elseif(preg_match('/^[a-z]$/', $char)) { + } elseif (preg_match('/^[a-z]$/', $char)) { $this->token = array( 'name' => strtoupper($char), 'type' => self::DOCTYPE, @@ -967,21 +1352,25 @@ class HTML5 { $this->state = 'doctypeName'; - } elseif($char === '>') { - $this->emitToken(array( - 'name' => null, - 'type' => self::DOCTYPE, - 'error' => true - )); + } elseif ($char === '>') { + $this->emitToken( + array( + 'name' => null, + 'type' => self::DOCTYPE, + 'error' => true + ) + ); $this->state = 'data'; - } elseif($this->char === $this->EOF) { - $this->emitToken(array( - 'name' => null, - 'type' => self::DOCTYPE, - 'error' => true - )); + } elseif ($this->char === $this->EOF) { + $this->emitToken( + array( + 'name' => null, + 'type' => self::DOCTYPE, + 'error' => true + ) + ); $this->char--; $this->state = 'data'; @@ -997,22 +1386,23 @@ class HTML5 { } } - private function doctypeNameState() { + private function doctypeNameState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { $this->state = 'AfterDoctypeName'; - } elseif($char === '>') { + } elseif ($char === '>') { $this->emitToken($this->token); $this->state = 'data'; - } elseif(preg_match('/^[a-z]$/', $char)) { + } elseif (preg_match('/^[a-z]$/', $char)) { $this->token['name'] .= strtoupper($char); - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { $this->emitToken($this->token); $this->char--; $this->state = 'data'; @@ -1026,19 +1416,20 @@ class HTML5 { : true; } - private function afterDoctypeNameState() { + private function afterDoctypeNameState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); - if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { // Stay in the DOCTYPE name state. - } elseif($char === '>') { + } elseif ($char === '>') { $this->emitToken($this->token); $this->state = 'data'; - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { $this->emitToken($this->token); $this->char--; $this->state = 'data'; @@ -1049,16 +1440,17 @@ class HTML5 { } } - private function bogusDoctypeState() { + private function bogusDoctypeState() + { /* Consume the next input character: */ $this->char++; $char = $this->char(); - if($char === '>') { + if ($char === '>') { $this->emitToken($this->token); $this->state = 'data'; - } elseif($this->char === $this->EOF) { + } elseif ($this->char === $this->EOF) { $this->emitToken($this->token); $this->char--; $this->state = 'data'; @@ -1068,22 +1460,23 @@ class HTML5 { } } - private function entity() { + private function entity() + { $start = $this->char; // This section defines how to consume an entity. This definition is // used when parsing entities in text and in attributes. // The behaviour depends on the identity of the next character (the - // one immediately after the U+0026 AMPERSAND character): + // one immediately after the U+0026 AMPERSAND character): - switch($this->character($this->char + 1)) { + switch ($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($this->char + 1)) { + switch ($this->character($this->char + 1)) { // U+0078 LATIN SMALL LETTER X // U+0058 LATIN CAPITAL LETTER X case 'x': @@ -1096,7 +1489,7 @@ class HTML5 { // words, 0-9, A-F, a-f). $char = 1; $char_class = '0-9A-Fa-f'; - break; + break; // Anything else default: @@ -1105,7 +1498,7 @@ class HTML5 { // NINE (i.e. just 0-9). $char = 0; $char_class = '0-9'; - break; + break; } // Consume as many characters as match the range of characters @@ -1116,7 +1509,7 @@ class HTML5 { $cond = strlen($e_name) > 0; // The rest of the parsing happens bellow. - break; + break; // Anything else default: @@ -1126,12 +1519,12 @@ class HTML5 { $e_name = $this->characters('0-9A-Za-z;', $this->char + 1); $len = strlen($e_name); - for($c = 1; $c <= $len; $c++) { + for ($c = 1; $c <= $len; $c++) { $id = substr($e_name, 0, $c); $this->char++; - if(in_array($id, $this->entities)) { - if ($e_name[$c-1] !== ';') { + if (in_array($id, $this->entities)) { + if ($e_name[$c - 1] !== ';') { if ($c < $len && $e_name[$c] == ';') { $this->char++; // consume extra semicolon } @@ -1143,10 +1536,10 @@ class HTML5 { $cond = isset($entity); // The rest of the parsing happens bellow. - break; + break; } - if(!$cond) { + if (!$cond) { // If no match can be made, then this is a parse error. No // characters are consumed, and nothing is returned. $this->char = $start; @@ -1155,81 +1548,157 @@ class HTML5 { // Return a character token for the character corresponding to the // entity name (as given by the second column of the entities table). - return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8'); + return html_entity_decode('&' . $entity . ';', ENT_QUOTES, 'UTF-8'); } - private function emitToken($token) { + private function emitToken($token) + { $emit = $this->tree->emitToken($token); - if(is_int($emit)) { + if (is_int($emit)) { $this->content_model = $emit; - } elseif($token['type'] === self::ENDTAG) { + } elseif ($token['type'] === self::ENDTAG) { $this->content_model = self::PCDATA; } } - private function EOF() { + private function EOF() + { $this->state = null; - $this->tree->emitToken(array( - 'type' => self::EOF - )); + $this->tree->emitToken( + array( + 'type' => self::EOF + ) + ); } } -class HTML5TreeConstructer { +class HTML5TreeConstructer +{ public $stack = array(); private $phase; private $mode; private $dom; private $foster_parent = null; - private $a_formatting = array(); + 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'); + 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; + const END_PHASE = 3; // The different insertion modes for the main phase. const BEFOR_HEAD = 0; - const IN_HEAD = 1; + const IN_HEAD = 1; const AFTER_HEAD = 2; - const IN_BODY = 3; - const IN_TABLE = 4; + 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 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 IN_FRAME = 12; const AFTR_FRAME = 13; // The different types of elements. - const SPECIAL = 0; - const SCOPING = 1; + const SPECIAL = 0; + const SCOPING = 1; const FORMATTING = 2; - const PHRASING = 3; + const PHRASING = 3; - const MARKER = 0; + const MARKER = 0; - public function __construct() { + public function __construct() + { $this->phase = self::INIT_PHASE; $this->mode = self::BEFOR_HEAD; $this->dom = new DOMDocument; @@ -1241,16 +1710,26 @@ class HTML5TreeConstructer { } // Process tag tokens - public function emitToken($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; + 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($token) { + private function initPhase($token) + { /* Initially, the tree construction stage must handle each token emitted from the tokenisation stage as follows: */ @@ -1262,13 +1741,14 @@ class HTML5TreeConstructer { 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($token['data']) && - !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) { + if ((isset($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 @@ -1277,8 +1757,8 @@ class HTML5TreeConstructer { $this->phase = self::ROOT_PHASE; return $this->rootElementPhase($token); - /* A DOCTYPE token marked as being correct */ - } elseif(isset($token['error']) && !$token['error']) { + /* 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 @@ -1289,52 +1769,58 @@ class HTML5TreeConstructer { 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 ]+$/', - $token['data'])) { + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif (isset($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($token) { + private function rootElementPhase($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($token['type'] === HTML5::DOCTYPE) { + if ($token['type'] === HTML5::DOCTYPE) { // Parse error. Ignore the token. - /* A comment token */ - } elseif($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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($token['type'] === HTML5::CHARACTR && - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif ($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 || - $token['type'] === HTML5::EOF) { + /* A character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED + (FF), or U+0020 SPACE + A start tag token + An end tag token + An end-of-file token */ + } elseif (($token['type'] === HTML5::CHARACTR && + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || + $token['type'] === HTML5::STARTTAG || + $token['type'] === HTML5::ENDTAG || + $token['type'] === HTML5::EOF + ) { /* Create an HTMLElement node with the tag name html, in the HTML namespace. Append it to the Document object. Switch to the main phase and reprocess the current token. */ @@ -1347,15 +1833,16 @@ class HTML5TreeConstructer { } } - private function mainPhase($token) { + private function mainPhase($token) + { /* Tokens in the main phase must be handled as follows: */ /* A DOCTYPE token */ - if($token['type'] === HTML5::DOCTYPE) { + if ($token['type'] === HTML5::DOCTYPE) { // Parse error. Ignore the token. - /* A start tag token with the tag name "html" */ - } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { + /* A start tag token with the tag name "html" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { /* If this start tag token was not the first start tag token, then it is a parse error. */ @@ -1363,59 +1850,91 @@ class HTML5TreeConstructer { is already present on the top element of the stack of open elements. If it is not, add the attribute and its corresponding value to that element. */ - foreach($token['attr'] as $attr) { - if(!$this->stack[0]->hasAttribute($attr['name'])) { + foreach ($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) { + /* An end-of-file token */ + } elseif ($token['type'] === HTML5::EOF) { /* Generate implied end tags. */ $this->generateImpliedEndTags(); - /* Anything else. */ + /* Anything else. */ } else { /* Depends on the insertion mode: */ - switch($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; + 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($token) { + private function beforeHead($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($token['type'] === HTML5::CHARACTR && - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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 && $token['name'] === 'head') { + /* A start tag token with the tag name "head" */ + } elseif ($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); @@ -1426,32 +1945,38 @@ class HTML5TreeConstructer { /* 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 ]$/', - $token['data']))) { + /* A start tag token whose tag name is one of: "base", "link", "meta", + "script", "style", "title". Or an end tag with the tag name "html". + Or a character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. Or any other start tag token */ + } elseif ($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() - )); + $this->beforeHead( + array( + 'name' => 'head', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); return $this->inHead($token); - /* Any other end tag */ - } elseif($token['type'] === HTML5::ENDTAG) { + /* Any other end tag */ + } elseif ($token['type'] === HTML5::ENDTAG) { /* Parse error. Ignore the token. */ } } - private function inHead($token) { + private function inHead($token) + { /* Handle the token as follows: */ /* A character token that is one of one of U+0009 CHARACTER TABULATION, @@ -1461,30 +1986,34 @@ class HTML5TreeConstructer { 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')))) { + 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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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'))) { + } 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 && $token['name'] === 'title') { + /* A start tag with the tag name "title" */ + } elseif ($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) { + if ($this->head_pointer !== null) { $element = $this->insertElement($token, false); $this->head_pointer->appendChild($element); @@ -1495,12 +2024,12 @@ class HTML5TreeConstructer { /* 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 && $token['name'] === 'style') { + /* A start tag with the tag name "style" */ + } elseif ($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) { + if ($this->head_pointer !== null) { $element = $this->insertElement($token, false); $this->head_pointer->appendChild($element); @@ -1511,8 +2040,8 @@ class HTML5TreeConstructer { /* 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 && $token['name'] === 'script') { + /* A start tag with the tag name "script" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { /* Create an element for the token. */ $element = $this->insertElement($token, false); $this->head_pointer->appendChild($element); @@ -1520,13 +2049,16 @@ class HTML5TreeConstructer { /* 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'))) { + /* 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) { + if ($this->head_pointer !== null) { $element = $this->insertElement($token, false); $this->head_pointer->appendChild($element); array_pop($this->stack); @@ -1535,14 +2067,14 @@ class HTML5TreeConstructer { $this->insertElement($token); } - /* An end tag with the tag name "head" */ - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { + /* An end tag with the tag name "head" */ + } elseif ($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($this->stack))) { + if ($this->head_pointer->isSameNode(end($this->stack))) { array_pop($this->stack); - /* Otherwise, this is a parse error. */ + /* Otherwise, this is a parse error. */ } else { // k } @@ -1550,22 +2082,25 @@ class HTML5TreeConstructer { /* 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 && $token['name'] !== 'html')) { + /* A start tag with the tag name "head" or an end tag except "html". */ + } elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || + ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html') + ) { // Parse error. Ignore the token. - /* Anything else */ + /* Anything else */ } else { /* If the current node is a head element, act as if an end tag token with the tag name "head" had been seen. */ - if($this->head_pointer->isSameNode(end($this->stack))) { - $this->inHead(array( - 'name' => 'head', - 'type' => HTML5::ENDTAG - )); + if ($this->head_pointer->isSameNode(end($this->stack))) { + $this->inHead( + array( + 'name' => 'head', + 'type' => HTML5::ENDTAG + ) + ); - /* Otherwise, change the insertion mode to "after head". */ + /* Otherwise, change the insertion mode to "after head". */ } else { $this->mode = self::AFTER_HEAD; } @@ -1575,66 +2110,74 @@ class HTML5TreeConstructer { } } - private function afterHead($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 ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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 && $token['name'] === 'body') { + /* A start tag token with the tag name "body" */ + } elseif ($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 && $token['name'] === 'frameset') { + /* A start tag token with the tag name "frameset" */ + } elseif ($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($token['name'], - array('base', 'link', 'meta', 'script', 'style', 'title'))) { + /* A start tag token whose tag name is one of: "base", "link", "meta", + "script", "style", "title" */ + } elseif ($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 */ + /* 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() - )); + $this->afterHead( + array( + 'name' => 'body', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); return $this->inBody($token); } } - private function inBody($token) { + private function inBody($token) + { /* Handle the token as follows: */ - switch($token['type']) { + switch ($token['type']) { /* A character token */ case HTML5::CHARACTR: /* Reconstruct the active formatting elements, if any. */ @@ -1642,1015 +2185,1159 @@ class HTML5TreeConstructer { /* Append the token's character to the current node. */ $this->insertText($token['data']); - break; + 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; + 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; + 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 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'], $attr['value']); + /* A start tag token with the tag name "body" */ + case 'body': + /* Parse error. If the second element on the stack of open + elements is not a body element, or, if the stack of open + elements has only one node on it, then ignore the token. + (innerHTML case) */ + if (count($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; + 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')) { - $this->emitToken(array( - 'name' => 'p', - 'type' => HTML5::ENDTAG - )); + /* A start tag whose tag name is one of: "address", + "blockquote", "center", "dir", "div", "dl", "fieldset", + "listing", "menu", "ol", "p", "ul" */ + case 'address': + case 'blockquote': + case 'center': + case 'dir': + case 'div': + case 'dl': + case 'fieldset': + case 'listing': + case 'menu': + case 'ol': + case 'p': + case 'ul': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); } - /* Insert an HTML element for the token, and set the - form element pointer to point to the element created. */ - $element = $this->insertElement($token); - $this->form_pointer = $element; - } - break; + /* Insert an HTML element for the token. */ + $this->insertElement($token); + 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')) { - $this->emitToken(array( - 'name' => 'p', - 'type' => HTML5::ENDTAG - )); - } + /* A start tag whose tag name is "form" */ + case 'form': + /* If the form element pointer is not null, ignore the + token with a parse error. */ + if ($this->form_pointer !== null) { + // Ignore. - $stack_length = count($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); + /* 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 + ) + ); } - break; + /* 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 = $element; } + break; - /* 3. If node is not in the formatting category, and is - not in the phrasing category, and is not an address or - div element, then stop this algorithm. */ - if($cat !== self::FORMATTING && $cat !== self::PHRASING && - $node->tagName !== 'address' && $node->tagName !== 'div') { - break; + /* A start tag whose tag name is "li", "dd" or "dt" */ + case 'li': + case 'dd': + case 'dt': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); } - } - /* Finally, insert an HTML element with the same tag - name as the token's. */ - $this->insertElement($token); - break; + $stack_length = count($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); + } - /* 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 - )); - } + break; + } - /* Insert an HTML element for the token. */ - $this->insertElement($token); + /* 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; + } + } - return HTML5::PLAINTEXT; - break; + /* Finally, insert an HTML element with the same tag + name as the token's. */ + $this->insertElement($token); + 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')) { - $this->emitToken(array( - 'name' => 'p', - 'type' => HTML5::ENDTAG - )); - } + /* A start tag token whose tag name is "plaintext" */ + case 'plaintext': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } - /* If the stack of open elements has in scope an element whose - tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then - this is a parse error; pop elements from the stack until an - element with one of those tag names has been popped from the - stack. */ - while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { - array_pop($this->stack); - } + /* Insert an HTML element for the token. */ + $this->insertElement($token); - /* Insert an HTML element for the token. */ - $this->insertElement($token); - break; + return HTML5::PLAINTEXT; + 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') { - $this->emitToken(array( - 'name' => 'a', - 'type' => HTML5::ENDTAG - )); - break; + /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4", + "h5", "h6" */ + case 'h1': + case 'h2': + case 'h3': + case 'h4': + case 'h5': + case 'h6': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); } - } - /* Reconstruct the active formatting elements, if any. */ - $this->reconstructActiveFormattingElements(); + /* If the stack of open elements has in scope an element whose + tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then + this is a parse error; pop elements from the stack until an + element with one of those tag names has been popped from the + stack. */ + while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { + array_pop($this->stack); + } - /* Insert an HTML element for the token. */ - $el = $this->insertElement($token); + /* Insert an HTML element for the token. */ + $this->insertElement($token); + break; - /* Add that element to the list of active formatting - elements. */ - $this->a_formatting[] = $el; - 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; - /* 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. */ - $this->reconstructActiveFormattingElements(); + } elseif ($this->a_formatting[$n]->nodeName === 'a') { + $this->emitToken( + array( + 'name' => 'a', + 'type' => HTML5::ENDTAG + ) + ); + break; + } + } - /* Insert an HTML element for the token. */ - $el = $this->insertElement($token); + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); - /* Add that element to the list of active formatting - elements. */ - $this->a_formatting[] = $el; - break; + /* Insert an HTML element for the token. */ + $el = $this->insertElement($token); - /* 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 - )); - } + /* Add that element to the list of active formatting + elements. */ + $this->a_formatting[] = $el; + break; - /* Reconstruct the active formatting elements, if any. */ - $this->reconstructActiveFormattingElements(); + /* 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; - /* Insert an HTML element for the token. */ - $this->insertElement($token); + /* 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 + ) + ); + } - /* Insert a marker at the end of the list of active - formatting elements. */ - $this->a_formatting[] = self::MARKER; - break; + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); - /* 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 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; - /* 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(); - /* 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); - /* 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; - /* Switch the content model flag to the CDATA state. */ - return HTML5::CDATA; - break; + /* A start tag token whose tag name is "xmp" */ + case 'xmp': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); - /* A start tag whose tag name is "table" */ - case 'table': - /* If the stack of open elements has a p element in scope, - then act as if an end tag with the tag name p had been seen. */ - if($this->elementInScope('p')) { - $this->emitToken(array( - 'name' => 'p', - 'type' => HTML5::ENDTAG - )); - } + /* Insert an HTML element for the token. */ + $this->insertElement($token); - /* Insert an HTML element for the token. */ - $this->insertElement($token); + /* Switch the content model flag to the CDATA state. */ + return HTML5::CDATA; + break; - /* Change the insertion mode to "in table". */ - $this->mode = self::IN_TABLE; - break; + /* A start tag whose tag name is "table" */ + case 'table': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } - /* 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); - /* Insert an HTML element for the token. */ - $this->insertElement($token); + /* Change the insertion mode to "in table". */ + $this->mode = self::IN_TABLE; + break; - /* Immediately pop the current node off the stack of open elements. */ - array_pop($this->stack); - 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')) { - $this->emitToken(array( - 'name' => 'p', - 'type' => HTML5::ENDTAG - )); - } + /* A start tag whose tag name is "hr" */ + case 'hr': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } - /* Insert an HTML element for the token. */ - $this->insertElement($token); + /* Insert an HTML element for the token. */ + $this->insertElement($token); - /* Immediately pop the current node off the stack of open elements. */ - array_pop($this->stack); - break; + /* Immediately pop the current node off the stack of open elements. */ + array_pop($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 "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(); + /* 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); + /* 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); + /* 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($this->stack); - break; + /* Pop that input element off the stack of open elements. */ + array_pop($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 "isindex" */ + case 'isindex': + /* Parse error. */ + // w/e - /* A start tag whose tag name is "textarea" */ - case 'textarea': - $this->insertElement($token); + /* 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; - /* Switch the tokeniser's content model flag to the - RCDATA state. */ - return HTML5::RCDATA; - break; + /* A start tag whose tag name is "textarea" */ + case 'textarea': + $this->insertElement($token); - /* 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 + RCDATA state. */ + return HTML5::RCDATA; + break; - /* Switch the tokeniser's content model flag to the CDATA state. */ - return HTML5::CDATA; - break; + /* A start tag whose tag name is one of: "iframe", "noembed", + "noframes" */ + case 'iframe': + case 'noembed': + case 'noframes': + $this->insertElement($token); - /* A start tag whose tag name is "select" */ - case 'select': - /* Reconstruct the active formatting elements, if any. */ - $this->reconstructActiveFormattingElements(); + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + break; - /* Insert an HTML element for the token. */ - $this->insertElement($token); + /* A start tag whose tag name is "select" */ + case 'select': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); - /* Change the insertion mode to "in select". */ - $this->mode = self::IN_SELECT; - break; + /* Insert an HTML element for the token. */ + $this->insertElement($token); - /* 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; + /* Change the insertion mode to "in select". */ + $this->mode = self::IN_SELECT; + 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 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 tag token not covered by the previous entries */ - default: - /* Reconstruct the active formatting elements, if any. */ - $this->reconstructActiveFormattingElements(); + /* 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); + $this->insertElement($token, true, true); + break; + } 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. - } + 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; + /* 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 - )); + /* 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; + 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'])) { - $this->generateImpliedEndTags(); - - /* Now, if the current node is not an element with - the same tag name as that of the token, then this - is a parse error. */ - // w/e + /* An end tag whose tag name is one of: "address", "blockquote", + "center", "dir", "div", "dl", "fieldset", "listing", "menu", + "ol", "pre", "ul" */ + case 'address': + case 'blockquote': + case 'center': + case 'dir': + case 'div': + case 'dl': + case 'fieldset': + case 'listing': + case 'menu': + case 'ol': + case 'pre': + case 'ul': + /* If the stack of open elements has an element in scope + with the same tag name as that of the token, then generate + implied end tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); - /* If the stack of open elements has an element in - scope with the same tag name as that of the token, - then pop elements from this stack until an element - with that tag name has been popped from the stack. */ - for($n = count($this->stack) - 1; $n >= 0; $n--) { - if($this->stack[$n]->nodeName === $token['name']) { - $n = -1; + /* Now, if the current node is not an element with + the same tag name as that of the token, then this + is a parse error. */ + // w/e + + /* If the stack of open elements has an element in + scope with the same tag name as that of the token, + then pop elements from this stack until an element + with that tag name has been popped from the stack. */ + for ($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'])) { + $this->generateImpliedEndTags(); - array_pop($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); + } - 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 + /* In any case, set the form element pointer to null. */ + $this->form_pointer = null; + break; - } else { - /* Otherwise, if the current node is an element with - the same tag name as that of the token pop that element - from the stack. */ - array_pop($this->stack); - } + /* 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')); - /* In any case, set the form element pointer to null. */ - $this->form_pointer = null; - break; + /* If the current node is not a p element, then this is + a parse error. */ + // k - /* An end tag whose tag name is "p" */ - case 'p': - /* If the stack of open elements has a p element in scope, - then generate implied end tags, except for p elements. */ - if($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($this->stack); + /* If the stack of open elements has a p element in + scope, then pop elements from this stack until the stack + no longer has a p element in scope. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->elementInScope('p')) { + array_pop($this->stack); - } else { - break; + } else { + break; + } } } - } - break; - - /* An end tag whose tag name is "dd", "dt", or "li" */ - case 'dd': case 'dt': case 'li': - /* If the stack of open elements has an element in scope - whose tag name matches the tag name of the token, then - generate implied end tags, except for elements with the - same tag name as the token. */ - if($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 + 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 - 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']) { - $n = -1; - } + generate implied end tags, except for elements with the + same tag name as the token. */ + if ($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); + 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': - $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'); + break; - /* If the stack of open elements has in scope an element whose - tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then - generate implied end tags. */ - if($this->elementInScope($elements)) { - $this->generateImpliedEndTags(); + /* 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)) { + $this->generateImpliedEndTags(); - /* Now, if the current node is not an element with the same - tag name as that of the token, then this is a parse error. */ - // w/e + /* Now, if the current node is not an element with the same + tag name as that of the token, then this is a parse error. */ + // w/e - /* If the stack of open elements has in scope an element - whose tag name is one of "h1", "h2", "h3", "h4", "h5", or - "h6", then pop elements from the stack until an element - with one of those tag names has been popped from the stack. */ - while($this->elementInScope($elements)) { - array_pop($this->stack); + /* 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($this->stack); + } } - } - break; + break; - /* An end tag whose tag name is one of: "a", "b", "big", "em", - "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ - case 'a': case 'b': case 'big': case 'em': case 'font': - case 'i': case 'nobr': case 's': case 'small': case 'strike': - case 'strong': case 'tt': case 'u': - /* 1. Let the formatting element be the last element in - the list of active formatting elements that: - * is between the end of the list and the last scope - marker in the list, if any, or the start of the list - otherwise, and - * has the same tag name as the token. - */ - while(true) { - for($a = count($this->a_formatting) - 1; $a >= 0; $a--) { - if($this->a_formatting[$a] === self::MARKER) { + /* An end tag whose tag name is one of: "a", "b", "big", "em", + "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ + case 'a': + case 'b': + case 'big': + case 'em': + case 'font': + case 'i': + case 'nobr': + case 's': + case 'small': + case 'strike': + case 'strong': + case 'tt': + case 'u': + /* 1. Let the formatting element be the last element in + the list of active formatting elements that: + * is between the end of the list and the last scope + marker in the list, if any, or the start of the list + otherwise, and + * has the same tag name as the token. + */ + while (true) { + for ($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($token['name'])) + ) { break; - } elseif($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 = $a; + /* Otherwise, if there is such a node, but that node + is not in the stack of open elements, then this is a + parse error; remove the element from the list, and + abort these steps. */ + } elseif (isset($formatting_element) && !$in_stack) { + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); break; } - } - - /* 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); + /* 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[$s]->nodeName); + for ($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]; + 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); - } + /* 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; - } + 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]; + /* 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); - } + /* 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); + /* 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; + } + } - } else { + /* 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, $this->a_formatting, true) + 1; } - } - /* 7.3 Otherwise, if node is the formatting - element, then go to the next step in the overall - algorithm. */ - if($node === $formatting_element) { - break; + /* 7.5 If node has any children, perform a + shallow clone of node, replace the entry for + node in the list of active formatting elements + with an entry for the clone, replace the entry + for node in the stack of open elements with an + entry for the clone, and let node be the clone. */ + if ($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 = $clone; + } - /* 7.4 Otherwise, if last node is the furthest - block, then move the aforementioned bookmark to - be immediately after the node in the list of - active formatting elements. */ - } elseif($last_node === $furthest_block) { - $bookmark = array_search($node, $this->a_formatting, true) + 1; - } + /* 7.6 Insert last node into node, first removing + it from its previous parent node if any. */ + if ($last_node->parentNode !== null) { + $last_node->parentNode->removeChild($last_node); + } + + $node->appendChild($last_node); - /* 7.5 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; + /* 7.7 Let last node be node. */ + $last_node = $node; } - /* 7.6 Insert last node into node, first removing - it from its previous parent node if any. */ - if($last_node->parentNode !== null) { + /* 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); } - $node->appendChild($last_node); + $common_ancestor->appendChild($last_node); - /* 7.7 Let last node be node. */ - $last_node = $node; - } + /* 9. Perform a shallow clone of the formatting + element. */ + $clone = $formatting_element->cloneNode(); - /* 8. Insert whatever last node ended up being in - the previous step into the common ancestor node, - first removing it from its previous parent node if - any. */ - if($last_node->parentNode !== null) { - $last_node->parentNode->removeChild($last_node); - } + /* 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); + } - $common_ancestor->appendChild($last_node); + /* 11. Append that clone to the furthest block. */ + $furthest_block->appendChild($clone); - /* 9. Perform a shallow clone of the formatting - element. */ - $clone = $formatting_element->cloneNode(); + /* 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); - /* 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); + $af_part1 = array_slice($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; - /* 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'])) { + $this->generateImpliedEndTags(); - /* An end tag token whose tag name is one of: "button", - "marquee", "object" */ - case 'button': case 'marquee': case 'object': - /* If the stack of open elements has an element in scope whose - tag name matches the tag name of the token, then generate implied - tags. */ - if($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']) { - $n = -1; - } + /* Now, if the current node is not an element with the same + tag name as the token, then this is a parse error. */ + // k - array_pop($this->stack); - } + /* 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; + } - $marker = end(array_keys($this->a_formatting, self::MARKER, true)); + array_pop($this->stack); + } - for($n = count($this->a_formatting) - 1; $n > $marker; $n--) { - array_pop($this->a_formatting); - } - } - break; + $marker = end(array_keys($this->a_formatting, self::MARKER, true)); - /* 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; + for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) { + array_pop($this->a_formatting); + } + } + 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. */ - $this->generateImpliedEndTags(); + /* Or an end tag whose tag name is one of: "area", "basefont", + "bgsound", "br", "embed", "hr", "iframe", "image", "img", + "input", "isindex", "noembed", "noframes", "param", "select", + "spacer", "table", "textarea", "wbr" */ + case 'area': + case 'basefont': + case 'bgsound': + case 'br': + case 'embed': + case 'hr': + case 'iframe': + case 'image': + case 'img': + case 'input': + case 'isindex': + case 'noembed': + case 'noframes': + case 'param': + case 'select': + case 'spacer': + case 'table': + case 'textarea': + case 'wbr': + // Parse error. Ignore the token. + break; - /* If the tag name of the end tag token does not - match the tag name of the current node, this is a - parse error. */ - // k + /* An end tag token not covered by the previous entries */ + default: + for ($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); + } - /* 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; + } else { + $category = $this->getElementCategory($node); + + if ($category !== self::SPECIAL && $category !== self::SCOPING) { + /* Otherwise, if node is in neither the formatting + category nor the phrasing category, then this is a + parse error. Stop this algorithm. The end tag token + is ignored. */ + return false; + } } } - } + break; + } break; - } - break; } } - private function inTable($token) { + 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 ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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 && - $token['name'] === 'caption') { + /* A start tag whose tag name is "caption" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'caption' + ) { /* Clear the stack back to a table context. */ $this->clearStackToTableContext($clear); @@ -2663,9 +3350,10 @@ class HTML5TreeConstructer { $this->insertElement($token); $this->mode = self::IN_CAPTION; - /* A start tag whose tag name is "colgroup" */ - } elseif($token['type'] === HTML5::STARTTAG && - $token['name'] === 'colgroup') { + /* A start tag whose tag name is "colgroup" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'colgroup' + ) { /* Clear the stack back to a table context. */ $this->clearStackToTableContext($clear); @@ -2674,20 +3362,26 @@ class HTML5TreeConstructer { $this->insertElement($token); $this->mode = self::IN_CGROUP; - /* A start tag whose tag name is "col" */ - } elseif($token['type'] === HTML5::STARTTAG && - $token['name'] === 'col') { - $this->inTable(array( - 'name' => 'colgroup', - 'type' => HTML5::STARTTAG, - 'attr' => array() - )); + /* A start tag whose tag name is "col" */ + } elseif ($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'))) { + /* 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); @@ -2696,42 +3390,49 @@ class HTML5TreeConstructer { $this->insertElement($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($token['name'], array('td', 'th', 'tr'))) { + /* A start tag whose tag name is one of: "td", "th", "tr" */ + } elseif ($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() - )); + $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 && - $token['name'] === 'table') { + /* A start tag whose tag name is "table" */ + } elseif ($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 - )); + $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 && - $token['name'] === 'table') { + /* An end tag whose tag name is "table" */ + } elseif ($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($token['name'], true)) { + if (!$this->elementInScope($token['name'], true)) { return false; - /* Otherwise: */ + /* Otherwise: */ } else { /* Generate implied end tags. */ $this->generateImpliedEndTags(); @@ -2742,11 +3443,11 @@ class HTML5TreeConstructer { /* Pop elements from this stack until a table element has been popped from the stack. */ - while(true) { + while (true) { $current = end($this->stack)->nodeName; array_pop($this->stack); - if($current === 'table') { + if ($current === 'table') { break; } } @@ -2755,14 +3456,28 @@ class HTML5TreeConstructer { $this->resetInsertionMode(); } - /* An end tag whose tag name is one of: "body", "caption", "col", - "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ - } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'], - array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td', - 'tfoot', 'th', 'thead', 'tr'))) { + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array( + 'body', + 'caption', + 'col', + 'colgroup', + 'html', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { // Parse error. Ignore the token. - /* Anything else */ + /* Anything else */ } else { /* Parse error. Process the token as if the insertion mode was "in body", with the following exception: */ @@ -2770,8 +3485,11 @@ class HTML5TreeConstructer { /* If the current node is a table, tbody, tfoot, thead, or tr element, then, whenever a node would be inserted into the current node, it must instead be inserted into the foster parent element. */ - if(in_array(end($this->stack)->nodeName, - array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { + if (in_array( + end($this->stack)->nodeName, + array('table', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { /* The foster parent element is the parent element of the last table element in the stack of open elements, if there is a table element and it has such a parent element. If there is no @@ -2783,21 +3501,22 @@ class HTML5TreeConstructer { its parent node is not an element, then the foster parent element is the element before the last table element in the stack of open elements. */ - for($n = count($this->stack) - 1; $n >= 0; $n--) { - if($this->stack[$n]->nodeName === 'table') { + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === 'table') { $table = $this->stack[$n]; break; } } - if(isset($table) && $table->parentNode !== null) { + if (isset($table) && $table->parentNode !== null) { $this->foster_parent = $table->parentNode; - } elseif(!isset($table)) { + } elseif (!isset($table)) { $this->foster_parent = $this->stack[0]; - } elseif(isset($table) && ($table->parentNode === null || - $table->parentNode->nodeType !== XML_ELEMENT_NODE)) { + } elseif (isset($table) && ($table->parentNode === null || + $table->parentNode->nodeType !== XML_ELEMENT_NODE) + ) { $this->foster_parent = $this->stack[$n - 1]; } } @@ -2806,16 +3525,17 @@ class HTML5TreeConstructer { } } - private function inCaption($token) { + private function inCaption($token) + { /* An end tag whose tag name is "caption" */ - if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { + if ($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($token['name'], true)) { + if (!$this->elementInScope($token['name'], true)) { // Ignore - /* Otherwise: */ + /* Otherwise: */ } else { /* Generate implied end tags. */ $this->generateImpliedEndTags(); @@ -2826,11 +3546,11 @@ class HTML5TreeConstructer { /* Pop elements from this stack until a caption element has been popped from the stack. */ - while(true) { + while (true) { $node = end($this->stack)->nodeName; array_pop($this->stack); - if($node === 'caption') { + if ($node === 'caption') { break; } } @@ -2843,99 +3563,131 @@ class HTML5TreeConstructer { $this->mode = self::IN_TABLE; } - /* A start tag whose tag name is one of: "caption", "col", "colgroup", - "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag - name is "table" */ - } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], - array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', - 'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG && - $token['name'] === 'table')) { + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag + name is "table" */ + } elseif (($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 - )); + $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'))) { + /* 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 */ + /* Anything else */ } else { /* Process the token as if the insertion mode was "in body". */ $this->inBody($token); } } - private function inColumnGroup($token) { + private function inColumnGroup($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($token['type'] === HTML5::CHARACTR && - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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 && $token['name'] === 'col') { + /* A start tag whose tag name is "col" */ + } elseif ($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 && - $token['name'] === 'colgroup') { + /* An end tag whose tag name is "colgroup" */ + } elseif ($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') { + if (end($this->stack)->nodeName === 'html') { // Ignore - /* Otherwise, pop the current node (which will be a colgroup - element) from the stack of open elements. Switch the insertion - mode to "in table". */ + /* Otherwise, pop the current node (which will be a colgroup + element) from the stack of open elements. Switch the insertion + mode to "in table". */ } else { array_pop($this->stack); $this->mode = self::IN_TABLE; } - /* An end tag whose tag name is "col" */ - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { + /* An end tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { /* Parse error. Ignore the token. */ - /* Anything else */ + /* 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 - )); + $this->inColumnGroup( + array( + 'name' => 'colgroup', + 'type' => HTML5::ENDTAG + ) + ); return $this->inTable($token); } } - private function inTableBody($token) { + private function inTableBody($token) + { $clear = array('tbody', 'tfoot', 'thead', 'html'); /* A start tag whose tag name is "tr" */ - if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { + if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { /* Clear the stack back to a table body context. */ $this->clearStackToTableContext($clear); @@ -2944,29 +3696,33 @@ class HTML5TreeConstructer { $this->insertElement($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' || $token['name'] === 'td')) { + /* A start tag whose tag name is one of: "th", "td" */ + } elseif ($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() - )); + $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'))) { + /* 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)) { + if (!$this->elementInScope($token['name'], true)) { // Ignore - /* Otherwise: */ + /* Otherwise: */ } else { /* Clear the stack back to a table body context. */ $this->clearStackToTableContext($clear); @@ -2977,18 +3733,21 @@ class HTML5TreeConstructer { $this->mode = self::IN_TABLE; } - /* A start tag whose tag name is one of: "caption", "col", "colgroup", - "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */ - } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'], - array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) || - ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) { + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */ + } elseif (($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)) { + if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { // Ignore. - /* Otherwise: */ + /* Otherwise: */ } else { /* Clear the stack back to a table body context. */ $this->clearStackToTableContext($clear); @@ -2996,33 +3755,40 @@ class HTML5TreeConstructer { /* 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 - )); + $this->inTableBody( + array( + 'name' => end($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'))) { + /* 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 */ + /* Anything else */ } else { /* Process the token as if the insertion mode was "in table". */ $this->inTable($token); } } - private function inRow($token) { + private function inRow($token) + { $clear = array('tr', 'html'); /* A start tag whose tag name is one of: "th", "td" */ - if($token['type'] === HTML5::STARTTAG && - ($token['name'] === 'th' || $token['name'] === 'td')) { + if ($token['type'] === HTML5::STARTTAG && + ($token['name'] === 'th' || $token['name'] === 'td') + ) { /* Clear the stack back to a table row context. */ $this->clearStackToTableContext($clear); @@ -3035,15 +3801,15 @@ class HTML5TreeConstructer { elements. */ $this->a_formatting[] = self::MARKER; - /* An end tag whose tag name is "tr" */ - } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { + /* An end tag whose tag name is "tr" */ + } elseif ($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($token['name'], true)) { + if (!$this->elementInScope($token['name'], true)) { // Ignore. - /* Otherwise: */ + /* Otherwise: */ } else { /* Clear the stack back to a table row context. */ $this->clearStackToTableContext($clear); @@ -3055,64 +3821,77 @@ class HTML5TreeConstructer { $this->mode = self::IN_TBODY; } - /* A start tag whose tag name is one of: "caption", "col", "colgroup", - "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */ - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], - array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) { + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */ + } elseif ($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 - )); + $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'))) { + /* 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)) { + if (!$this->elementInScope($token['name'], true)) { // Ignore. - /* Otherwise: */ + /* 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 - )); + $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'))) { + /* 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 */ + /* Anything else */ } else { /* Process the token as if the insertion mode was "in table". */ $this->inTable($token); } } - private function inCell($token) { + private function inCell($token) + { /* An end tag whose tag name is one of: "td", "th" */ - if($token['type'] === HTML5::ENDTAG && - ($token['name'] === 'td' || $token['name'] === 'th')) { + if ($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($token['name'], true)) { + if (!$this->elementInScope($token['name'], true)) { // Ignore. - /* Otherwise: */ + /* Otherwise: */ } else { /* Generate implied end tags, except for elements with the same tag name as the token. */ @@ -3124,11 +3903,11 @@ class HTML5TreeConstructer { /* Pop elements from this stack until an element with the same tag name as the token has been popped from the stack. */ - while(true) { + while (true) { $node = end($this->stack)->nodeName; array_pop($this->stack); - if($node === $token['name']) { + if ($node === $token['name']) { break; } } @@ -3142,178 +3921,223 @@ class HTML5TreeConstructer { $this->mode = self::IN_ROW; } - /* A start tag whose tag name is one of: "caption", "col", "colgroup", - "tbody", "td", "tfoot", "th", "thead", "tr" */ - } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'], - array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th', - 'thead', 'tr'))) { + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($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)) { + if (!$this->elementInScope(array('td', 'th'), true)) { // Ignore. - /* Otherwise, close the cell (see below) and reprocess the current - token. */ + /* 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'))) { + /* 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)) { + if (!$this->elementInScope(array('td', 'th'), true)) { // Ignore. - /* Otherwise, close the cell (see below) and reprocess the current - token. */ + /* 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'))) { + /* 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($token['name'], - array('table', 'tbody', 'tfoot', 'thead', 'tr'))) { + /* An end tag whose tag name is one of: "table", "tbody", "tfoot", + "thead", "tr" */ + } elseif ($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($token['name'], true)) { + if (!$this->elementInScope($token['name'], true)) { // Ignore. - /* Otherwise, close the cell (see below) and reprocess the current - token. */ + /* Otherwise, close the cell (see below) and reprocess the current + token. */ } else { $this->closeCell(); return $this->inRow($token); } - /* Anything else */ + /* Anything else */ } else { /* Process the token as if the insertion mode was "in body". */ $this->inBody($token); } } - private function inSelect($token) { + private function inSelect($token) + { /* Handle the token as follows: */ /* A character token */ - if($token['type'] === HTML5::CHARACTR) { + if ($token['type'] === HTML5::CHARACTR) { /* Append the token's character to the current node. */ $this->insertText($token['data']); - /* A comment token */ - } elseif($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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 && - $token['name'] === 'option') { + /* A start tag token whose tag name is "option" */ + } elseif ($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') { - $this->inSelect(array( - 'name' => 'option', - 'type' => HTML5::ENDTAG - )); + if (end($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 && - $token['name'] === 'optgroup') { + /* A start tag token whose tag name is "optgroup" */ + } elseif ($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') { - $this->inSelect(array( - 'name' => 'option', - 'type' => HTML5::ENDTAG - )); + if (end($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') { - $this->inSelect(array( - 'name' => 'optgroup', - 'type' => HTML5::ENDTAG - )); + if (end($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 && - $token['name'] === 'optgroup') { + /* An end tag token whose tag name is "optgroup" */ + } elseif ($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') { - $this->inSelect(array( - 'name' => 'option', - 'type' => HTML5::ENDTAG - )); + if ($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[$elements_in_stack - 1] === 'optgroup') { + if ($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 && - $token['name'] === 'option') { + /* An end tag token whose tag name is "option" */ + } elseif ($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') { + if (end($this->stack)->nodeName === 'option') { array_pop($this->stack); } - /* An end tag whose tag name is "select" */ - } elseif($token['type'] === HTML5::ENDTAG && - $token['name'] === 'select') { + /* An end tag whose tag name is "select" */ + } elseif ($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($token['name'], true)) { + if (!$this->elementInScope($token['name'], true)) { // w/e - /* Otherwise: */ + /* Otherwise: */ } else { /* Pop elements from the stack of open elements until a select element has been popped from the stack. */ - while(true) { + while (true) { $current = end($this->stack)->nodeName; array_pop($this->stack); - if($current === 'select') { + if ($current === 'select') { break; } } @@ -3322,20 +4146,35 @@ class HTML5TreeConstructer { $this->resetInsertionMode(); } - /* A start tag whose tag name is "select" */ - } elseif($token['name'] === 'select' && - $token['type'] === HTML5::STARTTAG) { + /* A start tag whose tag name is "select" */ + } elseif ($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) { + $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' + ) + ) && $token['type'] === HTML5::ENDTAG + ) { /* Parse error. */ // w/e @@ -3343,43 +4182,47 @@ class HTML5TreeConstructer { the same tag name as that of the token, then act as if an end tag with the tag name "select" had been seen, and reprocess the token. Otherwise, ignore the token. */ - if($this->elementInScope($token['name'], true)) { - $this->inSelect(array( - 'name' => 'select', - 'type' => HTML5::ENDTAG - )); + if ($this->elementInScope($token['name'], true)) { + $this->inSelect( + array( + 'name' => 'select', + 'type' => HTML5::ENDTAG + ) + ); $this->mainPhase($token); } - /* Anything else */ + /* Anything else */ } else { /* Parse error. Ignore the token. */ } } - private function afterBody($token) { + private function afterBody($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($token['type'] === HTML5::CHARACTR && - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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 && $token['name'] === 'html') { + /* An end tag with the tag name "html" */ + } elseif ($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 @@ -3388,7 +4231,7 @@ class HTML5TreeConstructer { /* Otherwise, switch to the trailing end phase. */ $this->phase = self::END_PHASE; - /* Anything else */ + /* Anything else */ } else { /* Parse error. Set the insertion mode to "in body" and reprocess the token. */ @@ -3397,34 +4240,38 @@ class HTML5TreeConstructer { } } - private function inFrameset($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 ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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' && - $token['type'] === HTML5::STARTTAG) { + /* A start tag with the tag name "frameset" */ + } elseif ($token['name'] === 'frameset' && + $token['type'] === HTML5::STARTTAG + ) { $this->insertElement($token); - /* An end tag with the tag name "frameset" */ - } elseif($token['name'] === 'frameset' && - $token['type'] === HTML5::ENDTAG) { + /* An end tag with the tag name "frameset" */ + } elseif ($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') { + if (end($this->stack)->nodeName === 'html') { // Ignore } else { @@ -3439,103 +4286,113 @@ class HTML5TreeConstructer { $this->mode = self::AFTR_FRAME; } - /* A start tag with the tag name "frame" */ - } elseif($token['name'] === 'frame' && - $token['type'] === HTML5::STARTTAG) { + /* A start tag with the tag name "frame" */ + } elseif ($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' && - $token['type'] === HTML5::STARTTAG) { + /* A start tag with the tag name "noframes" */ + } elseif ($token['name'] === 'noframes' && + $token['type'] === HTML5::STARTTAG + ) { /* Process the token as if the insertion mode had been "in body". */ $this->inBody($token); - /* Anything else */ + /* Anything else */ } else { /* Parse error. Ignore the token. */ } } - private function afterFrameset($token) { + private function afterFrameset($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($token['type'] === HTML5::CHARACTR && - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { + if ($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($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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' && - $token['type'] === HTML5::ENDTAG) { + /* An end tag with the tag name "html" */ + } elseif ($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' && - $token['type'] === HTML5::STARTTAG) { + /* A start tag with the tag name "noframes" */ + } elseif ($token['name'] === 'noframes' && + $token['type'] === HTML5::STARTTAG + ) { /* Process the token as if the insertion mode had been "in body". */ $this->inBody($token); - /* Anything else */ + /* Anything else */ } else { /* Parse error. Ignore the token. */ } } - private function trailingEndPhase($token) { + private function trailingEndPhase($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($token['type'] === HTML5::DOCTYPE) { + if ($token['type'] === HTML5::DOCTYPE) { // Parse error. Ignore the token. - /* A comment token */ - } elseif($token['type'] === HTML5::COMMENT) { + /* A comment token */ + } elseif ($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($token['type'] === HTML5::CHARACTR && - preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) { + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif ($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 || $token['type'] === HTML5::ENDTAG) { + /* A character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. Or a start tag token. Or an end tag token. */ + } elseif (($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($token['type'] === HTML5::EOF) { + /* An end-of-file token */ + } elseif ($token['type'] === HTML5::EOF) { /* OMG DONE!! */ } } - private function insertElement($token, $append = true, $check = false) { + private function insertElement($token, $append = true, $check = false) + { // Proprietary workaround for libxml2's limitations with tag names if ($check) { // Slightly modified HTML5 tag-name modification, @@ -3544,13 +4401,15 @@ class HTML5TreeConstructer { // 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'] === '') $token['name'] = 'span'; // arbitrary generic choice + if ($token['name'] === '') { + $token['name'] = 'span'; + } // arbitrary generic choice } - + $el = $this->dom->createElement($token['name']); - foreach($token['attr'] as $attr) { - if(!$el->hasAttribute($attr['name'])) { + foreach ($token['attr'] as $attr) { + if (!$el->hasAttribute($attr['name'])) { $el->setAttribute($attr['name'], $attr['value']); } } @@ -3561,48 +4420,54 @@ class HTML5TreeConstructer { return $el; } - private function insertText($data) { + private function insertText($data) + { $text = $this->dom->createTextNode($data); $this->appendToRealParent($text); } - private function insertComment($data) { + private function insertComment($data) + { $comment = $this->dom->createComment($data); $this->appendToRealParent($comment); } - private function appendToRealParent($node) { - if($this->foster_parent === null) { + private function appendToRealParent($node) + { + if ($this->foster_parent === null) { end($this->stack)->appendChild($node); - } elseif($this->foster_parent !== null) { + } elseif ($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) { + 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)) + if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) { $this->foster_parent->insertBefore($node, $table); - else + } 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, $table)) { + private function elementInScope($el, $table = false) + { + if (is_array($el)) { + foreach ($el as $element) { + if ($this->elementInScope($element, $table)) { return true; } } @@ -3612,28 +4477,38 @@ class HTML5TreeConstructer { $leng = count($this->stack); - for($n = 0; $n < $leng; $n++) { + for ($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 === $el) { + if ($node->tagName === $el) { /* 2. If node is the target node, terminate in a match state. */ return true; - } elseif($node->tagName === 'table') { + } elseif ($node->tagName === 'table') { /* 3. Otherwise, if node is a table element, terminate in a failure state. */ return false; - } elseif($table === true && in_array($node->tagName, array('caption', 'td', - 'th', 'button', 'marquee', 'object'))) { + } elseif ($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 === $node->ownerDocument->documentElement) { + } elseif ($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 @@ -3648,12 +4523,13 @@ class HTML5TreeConstructer { } } - private function reconstructActiveFormattingElements() { + 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($formatting_elements === 0) { + if ($formatting_elements === 0) { return false; } @@ -3665,14 +4541,14 @@ class HTML5TreeConstructer { 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, $this->stack, true)) { + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { return false; } - for($a = $formatting_elements - 1; $a >= 0; true) { + for ($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) { + if ($a === 0) { $step_seven = false; break; } @@ -3684,15 +4560,15 @@ class HTML5TreeConstructer { /* 6. If entry is neither a marker nor an element that is also in thetack of open elements, go to step 4. */ - if($entry === self::MARKER || in_array($entry, $this->stack, true)) { + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { break; } } - while(true) { + while (true) { /* 7. Let entry be the element one later than entry in the list of active formatting elements. */ - if(isset($step_seven) && $step_seven === true) { + if (isset($step_seven) && $step_seven === true) { $a++; $entry = $this->a_formatting[$a]; } @@ -3711,7 +4587,7 @@ class HTML5TreeConstructer { /* 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) !== $clone) { + if (end($this->a_formatting) !== $clone) { $step_seven = true; } else { break; @@ -3719,12 +4595,13 @@ class HTML5TreeConstructer { } } - private function clearTheActiveFormattingElementsUpToTheLastMarker() { + 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) { + while (true) { /* 1. Let entry be the last (most recently added) entry in the list of active formatting elements. */ $entry = end($this->a_formatting); @@ -3734,13 +4611,14 @@ class HTML5TreeConstructer { /* 3. If entry was a marker, then stop the algorithm at this point. The list has been cleared up to the last marker. */ - if($entry === self::MARKER) { + if ($entry === self::MARKER) { break; } } } - private function generateImpliedEndTags($exclude = array()) { + private function generateImpliedEndTags($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 @@ -3749,36 +4627,36 @@ class HTML5TreeConstructer { $node = end($this->stack); $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude); - while(in_array(end($this->stack)->nodeName, $elements)) { + while (in_array(end($this->stack)->nodeName, $elements)) { array_pop($this->stack); } } - private function getElementCategory($node) { + private function getElementCategory($node) + { $name = $node->tagName; - if(in_array($name, $this->special)) + if (in_array($name, $this->special)) { return self::SPECIAL; - - elseif(in_array($name, $this->scoping)) + } elseif (in_array($name, $this->scoping)) { return self::SCOPING; - - elseif(in_array($name, $this->formatting)) + } elseif (in_array($name, $this->formatting)) { return self::FORMATTING; - - else + } else { return self::PHRASING; + } } - private function clearStackToTableContext($elements) { + 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) { + while (true) { $node = end($this->stack)->nodeName; - if(in_array($node, $elements)) { + if (in_array($node, $elements)) { break; } else { array_pop($this->stack); @@ -3786,12 +4664,13 @@ class HTML5TreeConstructer { } } - private function resetInsertionMode() { + private function resetInsertionMode() + { /* 1. Let last be false. */ $last = false; $leng = count($this->stack); - for($n = $leng - 1; $n >= 0; $n--) { + for ($n = $leng - 1; $n >= 0; $n--) { /* 2. Let node be the last node in the stack of open elements. */ $node = $this->stack[$n]; @@ -3799,108 +4678,111 @@ class HTML5TreeConstructer { 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)) { + 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') { + 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' || $node->nodeName === 'th') { + /* 5. If node is a td or th element, then switch the insertion mode + to "in cell" and abort these steps. */ + } elseif ($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') { + /* 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'))) { + /* 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') { + /* 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') { + /* 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') { + /* 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') { + /* 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') { + /* 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') { + /* 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') { + /* 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($last) { + /* 15. If last is true, then set the insertion mode to "in body" + and abort these steps. (innerHTML case) */ + } elseif ($last) { $this->mode = self::IN_BODY; break; } } } - private function closeCell() { + 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 - )); + foreach (array('td', 'th') as $cell) { + if ($this->elementInScope($cell, true)) { + $this->inCell( + array( + 'name' => $cell, + 'type' => HTML5::ENDTAG + ) + ); break; } } } - public function save() { + public function save() + { return $this->dom; } } -?> diff --git a/library/HTMLPurifier/Node.php b/library/HTMLPurifier/Node.php new file mode 100644 index 000000000..3995fec9f --- /dev/null +++ b/library/HTMLPurifier/Node.php @@ -0,0 +1,49 @@ +<?php + +/** + * Abstract base node class that all others inherit from. + * + * Why do we not use the DOM extension? (1) It is not always available, + * (2) it has funny constraints on the data it can represent, + * whereas we want a maximally flexible representation, and (3) its + * interface is a bit cumbersome. + */ +abstract class HTMLPurifier_Node +{ + /** + * Line number of the start token in the source document + * @type int + */ + public $line; + + /** + * Column number of the start token in the source document. Null if unknown. + * @type int + */ + public $col; + + /** + * Lookup array of processing that this token is exempt from. + * Currently, valid values are "ValidateAttributes". + * @type array + */ + public $armor = array(); + + /** + * When true, this node should be ignored as non-existent. + * + * Who is responsible for ignoring dead nodes? FixNesting is + * responsible for removing them before passing on to child + * validators. + */ + public $dead = false; + + /** + * Returns a pair of start and end tokens, where the end token + * is null if it is not necessary. Does not include children. + * @type array + */ + abstract public function toTokenPair(); +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Node/Comment.php b/library/HTMLPurifier/Node/Comment.php new file mode 100644 index 000000000..38ba19394 --- /dev/null +++ b/library/HTMLPurifier/Node/Comment.php @@ -0,0 +1,36 @@ +<?php + +/** + * Concrete comment node class. + */ +class HTMLPurifier_Node_Comment extends HTMLPurifier_Node +{ + /** + * 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 = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Comment($this->data, $this->line, $this->col), null); + } +} diff --git a/library/HTMLPurifier/Node/Element.php b/library/HTMLPurifier/Node/Element.php new file mode 100644 index 000000000..6cbf56dad --- /dev/null +++ b/library/HTMLPurifier/Node/Element.php @@ -0,0 +1,59 @@ +<?php + +/** + * Concrete element node class. + */ +class HTMLPurifier_Node_Element extends HTMLPurifier_Node +{ + /** + * 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 node's attributes. + * @type array + */ + public $attr = array(); + + /** + * List of child elements. + * @type array + */ + public $children = array(); + + /** + * Does this use the <a></a> form or the </a> form, i.e. + * is it a pair of start/end tokens or an empty token. + * @bool + */ + public $empty = false; + + public $endCol = null, $endLine = null, $endArmor = array(); + + public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) { + $this->name = $name; + $this->attr = $attr; + $this->line = $line; + $this->col = $col; + $this->armor = $armor; + } + + public function toTokenPair() { + // XXX inefficiency here, normalization is not necessary + if ($this->empty) { + return array(new HTMLPurifier_Token_Empty($this->name, $this->attr, $this->line, $this->col, $this->armor), null); + } else { + $start = new HTMLPurifier_Token_Start($this->name, $this->attr, $this->line, $this->col, $this->armor); + $end = new HTMLPurifier_Token_End($this->name, array(), $this->endLine, $this->endCol, $this->endArmor); + //$end->start = $start; + return array($start, $end); + } + } +} + diff --git a/library/HTMLPurifier/Node/Text.php b/library/HTMLPurifier/Node/Text.php new file mode 100644 index 000000000..aec916647 --- /dev/null +++ b/library/HTMLPurifier/Node/Text.php @@ -0,0 +1,54 @@ +<?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_Node_Text extends HTMLPurifier_Node +{ + + /** + * PCDATA tag name compatible with DTD, see + * HTMLPurifier_ChildDef_Custom for details. + * @type string + */ + public $name = '#PCDATA'; + + /** + * @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, $is_whitespace, $line = null, $col = null) + { + $this->data = $data; + $this->is_whitespace = $is_whitespace; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Text($this->data, $this->line, $this->col), null); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/PercentEncoder.php b/library/HTMLPurifier/PercentEncoder.php index a43c44f4c..18c8bbb00 100644 --- a/library/HTMLPurifier/PercentEncoder.php +++ b/library/HTMLPurifier/PercentEncoder.php @@ -13,17 +13,26 @@ class HTMLPurifier_PercentEncoder /** * Reserved characters to preserve when using encode(). + * @type array */ protected $preserve = array(); /** * String of characters that should be preserved while using encode(). + * @param bool $preserve */ - public function __construct($preserve = false) { + public function __construct($preserve = false) + { // unreserved letters, ought to const-ify - for ($i = 48; $i <= 57; $i++) $this->preserve[$i] = true; // digits - for ($i = 65; $i <= 90; $i++) $this->preserve[$i] = true; // upper-case - for ($i = 97; $i <= 122; $i++) $this->preserve[$i] = true; // lower-case + for ($i = 48; $i <= 57; $i++) { // digits + $this->preserve[$i] = true; + } + for ($i = 65; $i <= 90; $i++) { // upper-case + $this->preserve[$i] = true; + } + for ($i = 97; $i <= 122; $i++) { // lower-case + $this->preserve[$i] = true; + } $this->preserve[45] = true; // Dash - $this->preserve[46] = true; // Period . $this->preserve[95] = true; // Underscore _ @@ -44,13 +53,14 @@ class HTMLPurifier_PercentEncoder * Assumes that the string has already been normalized, making any * and all percent escape sequences valid. Percents will not be * re-escaped, regardless of their status in $preserve - * @param $string String to be encoded - * @return Encoded string. + * @param string $string String to be encoded + * @return string Encoded string. */ - public function encode($string) { + public function encode($string) + { $ret = ''; for ($i = 0, $c = strlen($string); $i < $c; $i++) { - if ($string[$i] !== '%' && !isset($this->preserve[$int = ord($string[$i])]) ) { + if ($string[$i] !== '%' && !isset($this->preserve[$int = ord($string[$i])])) { $ret .= '%' . sprintf('%02X', $int); } else { $ret .= $string[$i]; @@ -64,10 +74,14 @@ class HTMLPurifier_PercentEncoder * @warning This function is affected by $preserve, even though the * usual desired behavior is for this not to preserve those * characters. Be careful when reusing instances of PercentEncoder! - * @param $string String to normalize + * @param string $string String to normalize + * @return string */ - public function normalize($string) { - if ($string == '') return ''; + public function normalize($string) + { + if ($string == '') { + return ''; + } $parts = explode('%', $string); $ret = array_shift($parts); foreach ($parts as $part) { @@ -92,7 +106,6 @@ class HTMLPurifier_PercentEncoder } return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Printer.php b/library/HTMLPurifier/Printer.php index e7eb82e83..549e4cea1 100644 --- a/library/HTMLPurifier/Printer.php +++ b/library/HTMLPurifier/Printer.php @@ -7,25 +7,30 @@ class HTMLPurifier_Printer { /** - * Instance of HTMLPurifier_Generator for HTML generation convenience funcs + * For HTML generation convenience funcs. + * @type HTMLPurifier_Generator */ protected $generator; /** - * Instance of HTMLPurifier_Config, for easy access + * For easy access. + * @type HTMLPurifier_Config */ protected $config; /** * Initialize $generator. */ - public function __construct() { + public function __construct() + { } /** * Give generator necessary configuration if possible + * @param HTMLPurifier_Config $config */ - public function prepareGenerator($config) { + public function prepareGenerator($config) + { $all = $config->getAll(); $context = new HTMLPurifier_Context(); $this->generator = new HTMLPurifier_Generator($config, $context); @@ -39,45 +44,62 @@ class HTMLPurifier_Printer /** * Returns a start tag - * @param $tag Tag name - * @param $attr Attribute array + * @param string $tag Tag name + * @param array $attr Attribute array + * @return string */ - protected function start($tag, $attr = array()) { + protected function start($tag, $attr = array()) + { return $this->generator->generateFromToken( - new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) - ); + new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) + ); } /** - * Returns an end teg - * @param $tag Tag name + * Returns an end tag + * @param string $tag Tag name + * @return string */ - protected function end($tag) { + protected function end($tag) + { return $this->generator->generateFromToken( - new HTMLPurifier_Token_End($tag) - ); + new HTMLPurifier_Token_End($tag) + ); } /** * Prints a complete element with content inside - * @param $tag Tag name - * @param $contents Element contents - * @param $attr Tag attributes - * @param $escape Bool whether or not to escape contents + * @param string $tag Tag name + * @param string $contents Element contents + * @param array $attr Tag attributes + * @param bool $escape whether or not to escape contents + * @return string */ - protected function element($tag, $contents, $attr = array(), $escape = true) { + protected function element($tag, $contents, $attr = array(), $escape = true) + { return $this->start($tag, $attr) . - ($escape ? $this->escape($contents) : $contents) . - $this->end($tag); + ($escape ? $this->escape($contents) : $contents) . + $this->end($tag); } - protected function elementEmpty($tag, $attr = array()) { + /** + * @param string $tag + * @param array $attr + * @return string + */ + protected function elementEmpty($tag, $attr = array()) + { return $this->generator->generateFromToken( new HTMLPurifier_Token_Empty($tag, $attr) ); } - protected function text($text) { + /** + * @param string $text + * @return string + */ + protected function text($text) + { return $this->generator->generateFromToken( new HTMLPurifier_Token_Text($text) ); @@ -85,24 +107,29 @@ class HTMLPurifier_Printer /** * Prints a simple key/value row in a table. - * @param $name Key - * @param $value Value + * @param string $name Key + * @param mixed $value Value + * @return string */ - protected function row($name, $value) { - if (is_bool($value)) $value = $value ? 'On' : 'Off'; + protected function row($name, $value) + { + if (is_bool($value)) { + $value = $value ? 'On' : 'Off'; + } return $this->start('tr') . "\n" . - $this->element('th', $name) . "\n" . - $this->element('td', $value) . "\n" . - $this->end('tr') - ; + $this->element('th', $name) . "\n" . + $this->element('td', $value) . "\n" . + $this->end('tr'); } /** * Escapes a string for HTML output. - * @param $string String to escape + * @param string $string String to escape + * @return string */ - protected function escape($string) { + protected function escape($string) + { $string = HTMLPurifier_Encoder::cleanUTF8($string); $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8'); return $string; @@ -110,32 +137,46 @@ class HTMLPurifier_Printer /** * Takes a list of strings and turns them into a single list - * @param $array List of strings - * @param $polite Bool whether or not to add an end before the last + * @param string[] $array List of strings + * @param bool $polite Bool whether or not to add an end before the last + * @return string */ - protected function listify($array, $polite = false) { - if (empty($array)) return 'None'; + protected function listify($array, $polite = false) + { + if (empty($array)) { + return 'None'; + } $ret = ''; $i = count($array); foreach ($array as $value) { $i--; $ret .= $value; - if ($i > 0 && !($polite && $i == 1)) $ret .= ', '; - if ($polite && $i == 1) $ret .= 'and '; + if ($i > 0 && !($polite && $i == 1)) { + $ret .= ', '; + } + if ($polite && $i == 1) { + $ret .= 'and '; + } } return $ret; } /** * Retrieves the class of an object without prefixes, as well as metadata - * @param $obj Object to determine class of - * @param $prefix Further prefix to remove + * @param object $obj Object to determine class of + * @param string $sec_prefix Further prefix to remove + * @return string */ - protected function getClass($obj, $sec_prefix = '') { + protected function getClass($obj, $sec_prefix = '') + { static $five = null; - if ($five === null) $five = version_compare(PHP_VERSION, '5', '>='); + if ($five === null) { + $five = version_compare(PHP_VERSION, '5', '>='); + } $prefix = 'HTMLPurifier_' . $sec_prefix; - if (!$five) $prefix = strtolower($prefix); + if (!$five) { + $prefix = strtolower($prefix); + } $class = str_replace($prefix, '', get_class($obj)); $lclass = strtolower($class); $class .= '('; @@ -164,13 +205,14 @@ class HTMLPurifier_Printer break; case 'css_importantdecorator': $class .= $this->getClass($obj->def, $sec_prefix); - if ($obj->allow) $class .= ', !important'; + if ($obj->allow) { + $class .= ', !important'; + } break; } $class .= ')'; return $class; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Printer/CSSDefinition.php b/library/HTMLPurifier/Printer/CSSDefinition.php index 81f986590..29505fe12 100644 --- a/library/HTMLPurifier/Printer/CSSDefinition.php +++ b/library/HTMLPurifier/Printer/CSSDefinition.php @@ -2,10 +2,17 @@ class HTMLPurifier_Printer_CSSDefinition extends HTMLPurifier_Printer { - + /** + * @type HTMLPurifier_CSSDefinition + */ protected $def; - public function render($config) { + /** + * @param HTMLPurifier_Config $config + * @return string + */ + public function render($config) + { $this->def = $config->getCSSDefinition(); $ret = ''; @@ -32,7 +39,6 @@ class HTMLPurifier_Printer_CSSDefinition extends HTMLPurifier_Printer return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Printer/ConfigForm.php b/library/HTMLPurifier/Printer/ConfigForm.php index 02aa65689..36100ce73 100644 --- a/library/HTMLPurifier/Printer/ConfigForm.php +++ b/library/HTMLPurifier/Printer/ConfigForm.php @@ -7,17 +7,20 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer { /** - * Printers for specific fields + * Printers for specific fields. + * @type HTMLPurifier_Printer[] */ protected $fields = array(); /** - * Documentation URL, can have fragment tagged on end + * Documentation URL, can have fragment tagged on end. + * @type string */ protected $docURL; /** - * Name of form element to stuff config in + * Name of form element to stuff config in. + * @type string */ protected $name; @@ -25,24 +28,27 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer * Whether or not to compress directive names, clipping them off * after a certain amount of letters. False to disable or integer letters * before clipping. + * @type bool */ protected $compress = false; /** - * @param $name Form element name for directives to be stuffed into - * @param $doc_url String documentation URL, will have fragment tagged on - * @param $compress Integer max length before compressing a directive name, set to false to turn off + * @param string $name Form element name for directives to be stuffed into + * @param string $doc_url String documentation URL, will have fragment tagged on + * @param bool $compress Integer max length before compressing a directive name, set to false to turn off */ public function __construct( - $name, $doc_url = null, $compress = false + $name, + $doc_url = null, + $compress = false ) { parent::__construct(); $this->docURL = $doc_url; - $this->name = $name; + $this->name = $name; $this->compress = $compress; // initialize sub-printers - $this->fields[0] = new HTMLPurifier_Printer_ConfigForm_default(); - $this->fields[HTMLPurifier_VarParser::BOOL] = new HTMLPurifier_Printer_ConfigForm_bool(); + $this->fields[0] = new HTMLPurifier_Printer_ConfigForm_default(); + $this->fields[HTMLPurifier_VarParser::BOOL] = new HTMLPurifier_Printer_ConfigForm_bool(); } /** @@ -50,32 +56,42 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer * @param $cols Integer columns of textarea, null to use default * @param $rows Integer rows of textarea, null to use default */ - public function setTextareaDimensions($cols = null, $rows = null) { - if ($cols) $this->fields['default']->cols = $cols; - if ($rows) $this->fields['default']->rows = $rows; + public function setTextareaDimensions($cols = null, $rows = null) + { + if ($cols) { + $this->fields['default']->cols = $cols; + } + if ($rows) { + $this->fields['default']->rows = $rows; + } } /** * Retrieves styling, in case it is not accessible by webserver */ - public static function getCSS() { + public static function getCSS() + { return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.css'); } /** * Retrieves JavaScript, in case it is not accessible by webserver */ - public static function getJavaScript() { + public static function getJavaScript() + { return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.js'); } /** * Returns HTML output for a configuration form - * @param $config Configuration object of current form state, or an array + * @param HTMLPurifier_Config|array $config Configuration object of current form state, or an array * where [0] has an HTML namespace and [1] is being rendered. - * @param $allowed Optional namespace(s) and directives to restrict form to. + * @param array|bool $allowed Optional namespace(s) and directives to restrict form to. + * @param bool $render_controls + * @return string */ - public function render($config, $allowed = true, $render_controls = true) { + public function render($config, $allowed = true, $render_controls = true) + { if (is_array($config) && isset($config[0])) { $gen_config = $config[0]; $config = $config[1]; @@ -91,29 +107,29 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer $all = array(); foreach ($allowed as $key) { list($ns, $directive) = $key; - $all[$ns][$directive] = $config->get($ns .'.'. $directive); + $all[$ns][$directive] = $config->get($ns . '.' . $directive); } $ret = ''; $ret .= $this->start('table', array('class' => 'hp-config')); $ret .= $this->start('thead'); $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Directive', array('class' => 'hp-directive')); - $ret .= $this->element('th', 'Value', array('class' => 'hp-value')); + $ret .= $this->element('th', 'Directive', array('class' => 'hp-directive')); + $ret .= $this->element('th', 'Value', array('class' => 'hp-value')); $ret .= $this->end('tr'); $ret .= $this->end('thead'); foreach ($all as $ns => $directives) { $ret .= $this->renderNamespace($ns, $directives); } if ($render_controls) { - $ret .= $this->start('tbody'); - $ret .= $this->start('tr'); - $ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls')); - $ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit')); - $ret .= '[<a href="?">Reset</a>]'; - $ret .= $this->end('td'); - $ret .= $this->end('tr'); - $ret .= $this->end('tbody'); + $ret .= $this->start('tbody'); + $ret .= $this->start('tr'); + $ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls')); + $ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit')); + $ret .= '[<a href="?">Reset</a>]'; + $ret .= $this->end('td'); + $ret .= $this->end('tr'); + $ret .= $this->end('tbody'); } $ret .= $this->end('table'); return $ret; @@ -122,13 +138,15 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer /** * Renders a single namespace * @param $ns String namespace name - * @param $directive Associative array of directives to values + * @param array $directives array of directives to values + * @return string */ - protected function renderNamespace($ns, $directives) { + protected function renderNamespace($ns, $directives) + { $ret = ''; $ret .= $this->start('tbody', array('class' => 'namespace')); $ret .= $this->start('tr'); - $ret .= $this->element('th', $ns, array('colspan' => 2)); + $ret .= $this->element('th', $ns, array('colspan' => 2)); $ret .= $this->end('tr'); $ret .= $this->end('tbody'); $ret .= $this->start('tbody'); @@ -139,40 +157,44 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer $url = str_replace('%s', urlencode("$ns.$directive"), $this->docURL); $ret .= $this->start('a', array('href' => $url)); } - $attr = array('for' => "{$this->name}:$ns.$directive"); - - // crop directive name if it's too long - if (!$this->compress || (strlen($directive) < $this->compress)) { - $directive_disp = $directive; - } else { - $directive_disp = substr($directive, 0, $this->compress - 2) . '...'; - $attr['title'] = $directive; - } + $attr = array('for' => "{$this->name}:$ns.$directive"); + + // crop directive name if it's too long + if (!$this->compress || (strlen($directive) < $this->compress)) { + $directive_disp = $directive; + } else { + $directive_disp = substr($directive, 0, $this->compress - 2) . '...'; + $attr['title'] = $directive; + } - $ret .= $this->element( - 'label', - $directive_disp, - // component printers must create an element with this id - $attr - ); - if ($this->docURL) $ret .= $this->end('a'); + $ret .= $this->element( + 'label', + $directive_disp, + // component printers must create an element with this id + $attr + ); + if ($this->docURL) { + $ret .= $this->end('a'); + } $ret .= $this->end('th'); $ret .= $this->start('td'); - $def = $this->config->def->info["$ns.$directive"]; - if (is_int($def)) { - $allow_null = $def < 0; - $type = abs($def); - } else { - $type = $def->type; - $allow_null = isset($def->allow_null); - } - if (!isset($this->fields[$type])) $type = 0; // default - $type_obj = $this->fields[$type]; - if ($allow_null) { - $type_obj = new HTMLPurifier_Printer_ConfigForm_NullDecorator($type_obj); - } - $ret .= $type_obj->render($ns, $directive, $value, $this->name, array($this->genConfig, $this->config)); + $def = $this->config->def->info["$ns.$directive"]; + if (is_int($def)) { + $allow_null = $def < 0; + $type = abs($def); + } else { + $type = $def->type; + $allow_null = isset($def->allow_null); + } + if (!isset($this->fields[$type])) { + $type = 0; + } // default + $type_obj = $this->fields[$type]; + if ($allow_null) { + $type_obj = new HTMLPurifier_Printer_ConfigForm_NullDecorator($type_obj); + } + $ret .= $type_obj->render($ns, $directive, $value, $this->name, array($this->genConfig, $this->config)); $ret .= $this->end('td'); $ret .= $this->end('tr'); } @@ -185,19 +207,33 @@ class HTMLPurifier_Printer_ConfigForm extends HTMLPurifier_Printer /** * Printer decorator for directives that accept null */ -class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer { +class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer +{ /** * Printer being decorated + * @type HTMLPurifier_Printer */ protected $obj; + /** - * @param $obj Printer to decorate + * @param HTMLPurifier_Printer $obj Printer to decorate */ - public function __construct($obj) { + public function __construct($obj) + { parent::__construct(); $this->obj = $obj; } - public function render($ns, $directive, $value, $name, $config) { + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { if (is_array($config) && isset($config[0])) { $gen_config = $config[0]; $config = $config[1]; @@ -215,15 +251,19 @@ class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer 'type' => 'checkbox', 'value' => '1', 'class' => 'null-toggle', - 'name' => "$name"."[Null_$ns.$directive]", + 'name' => "$name" . "[Null_$ns.$directive]", 'id' => "$name:Null_$ns.$directive", 'onclick' => "toggleWriteability('$name:$ns.$directive',checked)" // INLINE JAVASCRIPT!!!! ); if ($this->obj instanceof HTMLPurifier_Printer_ConfigForm_bool) { // modify inline javascript slightly - $attr['onclick'] = "toggleWriteability('$name:Yes_$ns.$directive',checked);toggleWriteability('$name:No_$ns.$directive',checked)"; + $attr['onclick'] = + "toggleWriteability('$name:Yes_$ns.$directive',checked);" . + "toggleWriteability('$name:No_$ns.$directive',checked)"; + } + if ($value === null) { + $attr['checked'] = 'checked'; } - if ($value === null) $attr['checked'] = 'checked'; $ret .= $this->elementEmpty('input', $attr); $ret .= $this->text(' or '); $ret .= $this->elementEmpty('br'); @@ -235,10 +275,28 @@ class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer /** * Swiss-army knife configuration form field printer */ -class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer { +class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer +{ + /** + * @type int + */ public $cols = 18; + + /** + * @type int + */ public $rows = 5; - public function render($ns, $directive, $value, $name, $config) { + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { if (is_array($config) && isset($config[0])) { $gen_config = $config[0]; $config = $config[1]; @@ -262,6 +320,7 @@ class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer { foreach ($array as $val => $b) { $value[] = $val; } + //TODO does this need a break? case HTMLPurifier_VarParser::ALIST: $value = implode(PHP_EOL, $value); break; @@ -281,25 +340,27 @@ class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer { $value = serialize($value); } $attr = array( - 'name' => "$name"."[$ns.$directive]", + 'name' => "$name" . "[$ns.$directive]", 'id' => "$name:$ns.$directive" ); - if ($value === null) $attr['disabled'] = 'disabled'; + if ($value === null) { + $attr['disabled'] = 'disabled'; + } if (isset($def->allowed)) { $ret .= $this->start('select', $attr); foreach ($def->allowed as $val => $b) { $attr = array(); - if ($value == $val) $attr['selected'] = 'selected'; + if ($value == $val) { + $attr['selected'] = 'selected'; + } $ret .= $this->element('option', $val, $attr); } $ret .= $this->end('select'); - } elseif ( - $type === HTMLPurifier_VarParser::TEXT || - $type === HTMLPurifier_VarParser::ITEXT || - $type === HTMLPurifier_VarParser::ALIST || - $type === HTMLPurifier_VarParser::HASH || - $type === HTMLPurifier_VarParser::LOOKUP - ) { + } elseif ($type === HTMLPurifier_VarParser::TEXT || + $type === HTMLPurifier_VarParser::ITEXT || + $type === HTMLPurifier_VarParser::ALIST || + $type === HTMLPurifier_VarParser::HASH || + $type === HTMLPurifier_VarParser::LOOKUP) { $attr['cols'] = $this->cols; $attr['rows'] = $this->rows; $ret .= $this->start('textarea', $attr); @@ -317,8 +378,18 @@ class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer { /** * Bool form field printer */ -class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer { - public function render($ns, $directive, $value, $name, $config) { +class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer +{ + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { if (is_array($config) && isset($config[0])) { $gen_config = $config[0]; $config = $config[1]; @@ -336,12 +407,16 @@ class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer { $attr = array( 'type' => 'radio', - 'name' => "$name"."[$ns.$directive]", + 'name' => "$name" . "[$ns.$directive]", 'id' => "$name:Yes_$ns.$directive", 'value' => '1' ); - if ($value === true) $attr['checked'] = 'checked'; - if ($value === null) $attr['disabled'] = 'disabled'; + if ($value === true) { + $attr['checked'] = 'checked'; + } + if ($value === null) { + $attr['disabled'] = 'disabled'; + } $ret .= $this->elementEmpty('input', $attr); $ret .= $this->start('label', array('for' => "$name:No_$ns.$directive")); @@ -351,12 +426,16 @@ class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer { $attr = array( 'type' => 'radio', - 'name' => "$name"."[$ns.$directive]", + 'name' => "$name" . "[$ns.$directive]", 'id' => "$name:No_$ns.$directive", 'value' => '0' ); - if ($value === false) $attr['checked'] = 'checked'; - if ($value === null) $attr['disabled'] = 'disabled'; + if ($value === false) { + $attr['checked'] = 'checked'; + } + if ($value === null) { + $attr['disabled'] = 'disabled'; + } $ret .= $this->elementEmpty('input', $attr); $ret .= $this->end('div'); diff --git a/library/HTMLPurifier/Printer/HTMLDefinition.php b/library/HTMLPurifier/Printer/HTMLDefinition.php index 8a8f126b8..5f2f2f8a7 100644 --- a/library/HTMLPurifier/Printer/HTMLDefinition.php +++ b/library/HTMLPurifier/Printer/HTMLDefinition.php @@ -4,11 +4,16 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer { /** - * Instance of HTMLPurifier_HTMLDefinition, for easy access + * @type HTMLPurifier_HTMLDefinition, for easy access */ protected $def; - public function render($config) { + /** + * @param HTMLPurifier_Config $config + * @return string + */ + public function render($config) + { $ret = ''; $this->config =& $config; @@ -28,8 +33,10 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Renders the Doctype table + * @return string */ - protected function renderDoctype() { + protected function renderDoctype() + { $doctype = $this->def->doctype; $ret = ''; $ret .= $this->start('table'); @@ -45,8 +52,10 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Renders environment table, which is miscellaneous info + * @return string */ - protected function renderEnvironment() { + protected function renderEnvironment() + { $def = $this->def; $ret = ''; @@ -59,28 +68,28 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer $ret .= $this->row('Block wrap name', $def->info_block_wrapper); $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Global attributes'); - $ret .= $this->element('td', $this->listifyAttr($def->info_global_attr),0,0); + $ret .= $this->element('th', 'Global attributes'); + $ret .= $this->element('td', $this->listifyAttr($def->info_global_attr), null, 0); $ret .= $this->end('tr'); $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Tag transforms'); - $list = array(); - foreach ($def->info_tag_transform as $old => $new) { - $new = $this->getClass($new, 'TagTransform_'); - $list[] = "<$old> with $new"; - } - $ret .= $this->element('td', $this->listify($list)); + $ret .= $this->element('th', 'Tag transforms'); + $list = array(); + foreach ($def->info_tag_transform as $old => $new) { + $new = $this->getClass($new, 'TagTransform_'); + $list[] = "<$old> with $new"; + } + $ret .= $this->element('td', $this->listify($list)); $ret .= $this->end('tr'); $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Pre-AttrTransform'); - $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre)); + $ret .= $this->element('th', 'Pre-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre)); $ret .= $this->end('tr'); $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Post-AttrTransform'); - $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post)); + $ret .= $this->element('th', 'Post-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post)); $ret .= $this->end('tr'); $ret .= $this->end('table'); @@ -89,8 +98,10 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Renders the Content Sets table + * @return string */ - protected function renderContentSets() { + protected function renderContentSets() + { $ret = ''; $ret .= $this->start('table'); $ret .= $this->element('caption', 'Content Sets'); @@ -106,8 +117,10 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Renders the Elements ($info) table + * @return string */ - protected function renderInfo() { + protected function renderInfo() + { $ret = ''; $ret .= $this->start('table'); $ret .= $this->element('caption', 'Elements ($info)'); @@ -118,39 +131,39 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer $ret .= $this->end('tr'); foreach ($this->def->info as $name => $def) { $ret .= $this->start('tr'); - $ret .= $this->element('th', "<$name>", array('class'=>'heavy', 'colspan' => 2)); + $ret .= $this->element('th', "<$name>", array('class' => 'heavy', 'colspan' => 2)); $ret .= $this->end('tr'); $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Inline content'); - $ret .= $this->element('td', $def->descendants_are_inline ? 'Yes' : 'No'); + $ret .= $this->element('th', 'Inline content'); + $ret .= $this->element('td', $def->descendants_are_inline ? 'Yes' : 'No'); $ret .= $this->end('tr'); if (!empty($def->excludes)) { $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Excludes'); - $ret .= $this->element('td', $this->listifyTagLookup($def->excludes)); + $ret .= $this->element('th', 'Excludes'); + $ret .= $this->element('td', $this->listifyTagLookup($def->excludes)); $ret .= $this->end('tr'); } if (!empty($def->attr_transform_pre)) { $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Pre-AttrTransform'); - $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre)); + $ret .= $this->element('th', 'Pre-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre)); $ret .= $this->end('tr'); } if (!empty($def->attr_transform_post)) { $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Post-AttrTransform'); - $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post)); + $ret .= $this->element('th', 'Post-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post)); $ret .= $this->end('tr'); } if (!empty($def->auto_close)) { $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Auto closed by'); - $ret .= $this->element('td', $this->listifyTagLookup($def->auto_close)); + $ret .= $this->element('th', 'Auto closed by'); + $ret .= $this->element('td', $this->listifyTagLookup($def->auto_close)); $ret .= $this->end('tr'); } $ret .= $this->start('tr'); - $ret .= $this->element('th', 'Allowed attributes'); - $ret .= $this->element('td',$this->listifyAttr($def->attr), array(), 0); + $ret .= $this->element('th', 'Allowed attributes'); + $ret .= $this->element('td', $this->listifyAttr($def->attr), array(), 0); $ret .= $this->end('tr'); if (!empty($def->required_attr)) { @@ -165,64 +178,94 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Renders a row describing the allowed children of an element - * @param $def HTMLPurifier_ChildDef of pertinent element + * @param HTMLPurifier_ChildDef $def HTMLPurifier_ChildDef of pertinent element + * @return string */ - protected function renderChildren($def) { + protected function renderChildren($def) + { $context = new HTMLPurifier_Context(); $ret = ''; $ret .= $this->start('tr'); - $elements = array(); - $attr = array(); - if (isset($def->elements)) { - if ($def->type == 'strictblockquote') { - $def->validateChildren(array(), $this->config, $context); - } - $elements = $def->elements; + $elements = array(); + $attr = array(); + if (isset($def->elements)) { + if ($def->type == 'strictblockquote') { + $def->validateChildren(array(), $this->config, $context); } - if ($def->type == 'chameleon') { - $attr['rowspan'] = 2; - } elseif ($def->type == 'empty') { - $elements = array(); - } elseif ($def->type == 'table') { - $elements = array_flip(array('col', 'caption', 'colgroup', 'thead', - 'tfoot', 'tbody', 'tr')); - } - $ret .= $this->element('th', 'Allowed children', $attr); - - if ($def->type == 'chameleon') { - - $ret .= $this->element('td', - '<em>Block</em>: ' . - $this->escape($this->listifyTagLookup($def->block->elements)),0,0); - $ret .= $this->end('tr'); - $ret .= $this->start('tr'); - $ret .= $this->element('td', - '<em>Inline</em>: ' . - $this->escape($this->listifyTagLookup($def->inline->elements)),0,0); - - } elseif ($def->type == 'custom') { + $elements = $def->elements; + } + if ($def->type == 'chameleon') { + $attr['rowspan'] = 2; + } elseif ($def->type == 'empty') { + $elements = array(); + } elseif ($def->type == 'table') { + $elements = array_flip( + array( + 'col', + 'caption', + 'colgroup', + 'thead', + 'tfoot', + 'tbody', + 'tr' + ) + ); + } + $ret .= $this->element('th', 'Allowed children', $attr); - $ret .= $this->element('td', '<em>'.ucfirst($def->type).'</em>: ' . - $def->dtd_regex); + if ($def->type == 'chameleon') { - } else { - $ret .= $this->element('td', - '<em>'.ucfirst($def->type).'</em>: ' . - $this->escape($this->listifyTagLookup($elements)),0,0); - } + $ret .= $this->element( + 'td', + '<em>Block</em>: ' . + $this->escape($this->listifyTagLookup($def->block->elements)), + null, + 0 + ); + $ret .= $this->end('tr'); + $ret .= $this->start('tr'); + $ret .= $this->element( + 'td', + '<em>Inline</em>: ' . + $this->escape($this->listifyTagLookup($def->inline->elements)), + null, + 0 + ); + + } elseif ($def->type == 'custom') { + + $ret .= $this->element( + 'td', + '<em>' . ucfirst($def->type) . '</em>: ' . + $def->dtd_regex + ); + + } else { + $ret .= $this->element( + 'td', + '<em>' . ucfirst($def->type) . '</em>: ' . + $this->escape($this->listifyTagLookup($elements)), + null, + 0 + ); + } $ret .= $this->end('tr'); return $ret; } /** * Listifies a tag lookup table. - * @param $array Tag lookup array in form of array('tagname' => true) + * @param array $array Tag lookup array in form of array('tagname' => true) + * @return string */ - protected function listifyTagLookup($array) { + protected function listifyTagLookup($array) + { ksort($array); $list = array(); foreach ($array as $name => $discard) { - if ($name !== '#PCDATA' && !isset($this->def->info[$name])) continue; + if ($name !== '#PCDATA' && !isset($this->def->info[$name])) { + continue; + } $list[] = $name; } return $this->listify($list); @@ -230,13 +273,15 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Listifies a list of objects by retrieving class names and internal state - * @param $array List of objects + * @param array $array List of objects + * @return string * @todo Also add information about internal state */ - protected function listifyObjectList($array) { + protected function listifyObjectList($array) + { ksort($array); $list = array(); - foreach ($array as $discard => $obj) { + foreach ($array as $obj) { $list[] = $this->getClass($obj, 'AttrTransform_'); } return $this->listify($list); @@ -244,13 +289,17 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Listifies a hash of attributes to AttrDef classes - * @param $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef) + * @param array $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef) + * @return string */ - protected function listifyAttr($array) { + protected function listifyAttr($array) + { ksort($array); $list = array(); foreach ($array as $name => $obj) { - if ($obj === false) continue; + if ($obj === false) { + continue; + } $list[] = "$name = <i>" . $this->getClass($obj, 'AttrDef_') . '</i>'; } return $this->listify($list); @@ -258,15 +307,18 @@ class HTMLPurifier_Printer_HTMLDefinition extends HTMLPurifier_Printer /** * Creates a heavy header row + * @param string $text + * @param int $num + * @return string */ - protected function heavyHeader($text, $num = 1) { + protected function heavyHeader($text, $num = 1) + { $ret = ''; $ret .= $this->start('tr'); $ret .= $this->element('th', $text, array('colspan' => $num, 'class' => 'heavy')); $ret .= $this->end('tr'); return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/PropertyList.php b/library/HTMLPurifier/PropertyList.php index 2b99fb7bc..189348fd9 100644 --- a/library/HTMLPurifier/PropertyList.php +++ b/library/HTMLPurifier/PropertyList.php @@ -6,61 +6,93 @@ class HTMLPurifier_PropertyList { /** - * Internal data-structure for properties + * Internal data-structure for properties. + * @type array */ protected $data = array(); /** - * Parent plist + * Parent plist. + * @type HTMLPurifier_PropertyList */ protected $parent; + /** + * Cache. + * @type array + */ protected $cache; - public function __construct($parent = null) { + /** + * @param HTMLPurifier_PropertyList $parent Parent plist + */ + public function __construct($parent = null) + { $this->parent = $parent; } /** * Recursively retrieves the value for a key + * @param string $name + * @throws HTMLPurifier_Exception */ - public function get($name) { - if ($this->has($name)) return $this->data[$name]; + public function get($name) + { + if ($this->has($name)) { + return $this->data[$name]; + } // possible performance bottleneck, convert to iterative if necessary - if ($this->parent) return $this->parent->get($name); + if ($this->parent) { + return $this->parent->get($name); + } throw new HTMLPurifier_Exception("Key '$name' not found"); } /** * Sets the value of a key, for this plist + * @param string $name + * @param mixed $value */ - public function set($name, $value) { + public function set($name, $value) + { $this->data[$name] = $value; } /** * Returns true if a given key exists + * @param string $name + * @return bool */ - public function has($name) { + public function has($name) + { return array_key_exists($name, $this->data); } /** * Resets a value to the value of it's parent, usually the default. If * no value is specified, the entire plist is reset. + * @param string $name */ - public function reset($name = null) { - if ($name == null) $this->data = array(); - else unset($this->data[$name]); + public function reset($name = null) + { + if ($name == null) { + $this->data = array(); + } else { + unset($this->data[$name]); + } } /** * Squashes this property list and all of its property lists into a single * array, and returns the array. This value is cached by default. - * @param $force If true, ignores the cache and regenerates the array. + * @param bool $force If true, ignores the cache and regenerates the array. + * @return array */ - public function squash($force = false) { - if ($this->cache !== null && !$force) return $this->cache; + public function squash($force = false) + { + if ($this->cache !== null && !$force) { + return $this->cache; + } if ($this->parent) { return $this->cache = array_merge($this->parent->squash($force), $this->data); } else { @@ -70,15 +102,19 @@ class HTMLPurifier_PropertyList /** * Returns the parent plist. + * @return HTMLPurifier_PropertyList */ - public function getParent() { + public function getParent() + { return $this->parent; } /** * Sets the parent plist. + * @param HTMLPurifier_PropertyList $plist Parent plist */ - public function setParent($plist) { + public function setParent($plist) + { $this->parent = $plist; } } diff --git a/library/HTMLPurifier/PropertyListIterator.php b/library/HTMLPurifier/PropertyListIterator.php index 8f250443e..15b330ea3 100644 --- a/library/HTMLPurifier/PropertyListIterator.php +++ b/library/HTMLPurifier/PropertyListIterator.php @@ -6,27 +6,37 @@ class HTMLPurifier_PropertyListIterator extends FilterIterator { + /** + * @type int + */ protected $l; + /** + * @type string + */ protected $filter; /** - * @param $data Array of data to iterate over - * @param $filter Optional prefix to only allow values of + * @param Iterator $iterator Array of data to iterate over + * @param string $filter Optional prefix to only allow values of */ - public function __construct(Iterator $iterator, $filter = null) { + public function __construct(Iterator $iterator, $filter = null) + { parent::__construct($iterator); $this->l = strlen($filter); $this->filter = $filter; } - public function accept() { + /** + * @return bool + */ + public function accept() + { $key = $this->getInnerIterator()->key(); - if( strncmp($key, $this->filter, $this->l) !== 0 ) { + if (strncmp($key, $this->filter, $this->l) !== 0) { return false; } return true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Queue.php b/library/HTMLPurifier/Queue.php new file mode 100644 index 000000000..f58db9042 --- /dev/null +++ b/library/HTMLPurifier/Queue.php @@ -0,0 +1,56 @@ +<?php + +/** + * A simple array-backed queue, based off of the classic Okasaki + * persistent amortized queue. The basic idea is to maintain two + * stacks: an input stack and an output stack. When the output + * stack runs out, reverse the input stack and use it as the output + * stack. + * + * We don't use the SPL implementation because it's only supported + * on PHP 5.3 and later. + * + * Exercise: Prove that push/pop on this queue take amortized O(1) time. + * + * Exercise: Extend this queue to be a deque, while preserving amortized + * O(1) time. Some care must be taken on rebalancing to avoid quadratic + * behaviour caused by repeatedly shuffling data from the input stack + * to the output stack and back. + */ +class HTMLPurifier_Queue { + private $input; + private $output; + + public function __construct($input = array()) { + $this->input = $input; + $this->output = array(); + } + + /** + * Shifts an element off the front of the queue. + */ + public function shift() { + if (empty($this->output)) { + $this->output = array_reverse($this->input); + $this->input = array(); + } + if (empty($this->output)) { + return NULL; + } + return array_pop($this->output); + } + + /** + * Pushes an element onto the front of the queue. + */ + public function push($x) { + array_push($this->input, $x); + } + + /** + * Checks if it's empty. + */ + public function isEmpty() { + return empty($this->input) && empty($this->output); + } +} diff --git a/library/HTMLPurifier/Strategy.php b/library/HTMLPurifier/Strategy.php index 246286521..e1ff3b72d 100644 --- a/library/HTMLPurifier/Strategy.php +++ b/library/HTMLPurifier/Strategy.php @@ -15,12 +15,12 @@ abstract class HTMLPurifier_Strategy /** * Executes the strategy on the tokens. * - * @param $tokens Array of HTMLPurifier_Token objects to be operated on. - * @param $config Configuration options - * @returns Processed array of token objects. + * @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token objects to be operated on. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] Processed array of token objects. */ abstract public function execute($tokens, $config, $context); - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Strategy/Composite.php b/library/HTMLPurifier/Strategy/Composite.php index 816490b79..d7d35ce7d 100644 --- a/library/HTMLPurifier/Strategy/Composite.php +++ b/library/HTMLPurifier/Strategy/Composite.php @@ -8,18 +8,23 @@ abstract class HTMLPurifier_Strategy_Composite extends HTMLPurifier_Strategy /** * List of strategies to run tokens through. + * @type HTMLPurifier_Strategy[] */ protected $strategies = array(); - abstract public function __construct(); - - public function execute($tokens, $config, $context) { + /** + * @param HTMLPurifier_Token[] $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] + */ + public function execute($tokens, $config, $context) + { foreach ($this->strategies as $strategy) { $tokens = $strategy->execute($tokens, $config, $context); } return $tokens; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Strategy/Core.php b/library/HTMLPurifier/Strategy/Core.php index d90e15860..4414c17d6 100644 --- a/library/HTMLPurifier/Strategy/Core.php +++ b/library/HTMLPurifier/Strategy/Core.php @@ -5,14 +5,13 @@ */ class HTMLPurifier_Strategy_Core extends HTMLPurifier_Strategy_Composite { - - public function __construct() { + public function __construct() + { $this->strategies[] = new HTMLPurifier_Strategy_RemoveForeignElements(); $this->strategies[] = new HTMLPurifier_Strategy_MakeWellFormed(); $this->strategies[] = new HTMLPurifier_Strategy_FixNesting(); $this->strategies[] = new HTMLPurifier_Strategy_ValidateAttributes(); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Strategy/FixNesting.php b/library/HTMLPurifier/Strategy/FixNesting.php index f81802391..6fa673db9 100644 --- a/library/HTMLPurifier/Strategy/FixNesting.php +++ b/library/HTMLPurifier/Strategy/FixNesting.php @@ -10,12 +10,12 @@ * document type definitions, such as the chameleon nature of ins/del * tags and global child exclusions. * - * The first major objective of this strategy is to iterate through all the - * nodes (not tokens) of the list of tokens and determine whether or not - * their children conform to the element's definition. If they do not, the - * child definition may optionally supply an amended list of elements that - * is valid or require that the entire node be deleted (and the previous - * node rescanned). + * The first major objective of this strategy is to iterate through all + * the nodes and determine whether or not their children conform to the + * element's definition. If they do not, the child definition may + * optionally supply an amended list of elements that is valid or + * require that the entire node be deleted (and the previous node + * rescanned). * * The second objective is to ensure that explicitly excluded elements of * an element do not appear in its children. Code that accomplishes this @@ -25,24 +25,33 @@ * @note Whether or not unrecognized children are silently dropped or * translated into text depends on the child definitions. * - * @todo Enable nodes to be bubbled out of the structure. + * @todo Enable nodes to be bubbled out of the structure. This is + * easier with our new algorithm. */ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy { - public function execute($tokens, $config, $context) { + /** + * @param HTMLPurifier_Token[] $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array|HTMLPurifier_Token[] + */ + public function execute($tokens, $config, $context) + { + //####################################################################// // Pre-processing + // O(n) pass to convert to a tree, so that we can efficiently + // refer to substrings + $top_node = HTMLPurifier_Arborize::arborize($tokens, $config, $context); + // get a copy of the HTML definition $definition = $config->getHTMLDefinition(); - // insert implicit "parent" node, will be removed at end. - // DEFINITION CALL - $parent_name = $definition->info_parent; - array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name)); - $tokens[] = new HTMLPurifier_Token_End($parent_name); + $excludes_enabled = !$config->get('Core.DisableExcludes'); // setup the context variable 'IsInline', for chameleon processing // is 'false' when we are not inline, 'true' when it must always @@ -57,272 +66,116 @@ class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy //####################################################################// // Loop initialization - // stack that contains the indexes of all parents, - // $stack[count($stack)-1] being the current parent - $stack = array(); - // stack that contains all elements that are excluded // it is organized by parent elements, similar to $stack, // but it is only populated when an element with exclusions is // processed, i.e. there won't be empty exclusions. - $exclude_stack = array(); + $exclude_stack = array($definition->info_parent_def->excludes); // variable that contains the start token while we are processing // nodes. This enables error reporting to do its job - $start_token = false; - $context->register('CurrentToken', $start_token); + $node = $top_node; + // dummy token + list($token, $d) = $node->toTokenPair(); + $context->register('CurrentNode', $node); + $context->register('CurrentToken', $token); //####################################################################// // Loop - // iterate through all start nodes. Determining the start node - // is complicated so it has been omitted from the loop construct - for ($i = 0, $size = count($tokens) ; $i < $size; ) { - - //################################################################// - // Gather information on children - - // child token accumulator - $child_tokens = array(); - - // scroll to the end of this node, report number, and collect - // all children - for ($j = $i, $depth = 0; ; $j++) { - if ($tokens[$j] instanceof HTMLPurifier_Token_Start) { - $depth++; - // skip token assignment on first iteration, this is the - // token we currently are on - if ($depth == 1) continue; - } elseif ($tokens[$j] instanceof HTMLPurifier_Token_End) { - $depth--; - // skip token assignment on last iteration, this is the - // end token of the token we're currently on - if ($depth == 0) break; - } - $child_tokens[] = $tokens[$j]; - } - - // $i is index of start token - // $j is index of end token - - $start_token = $tokens[$i]; // to make token available via CurrentToken - - //################################################################// - // Gather information on parent - - // calculate parent information - if ($count = count($stack)) { - $parent_index = $stack[$count-1]; - $parent_name = $tokens[$parent_index]->name; - if ($parent_index == 0) { - $parent_def = $definition->info_parent_def; - } else { - $parent_def = $definition->info[$parent_name]; - } - } else { - // processing as if the parent were the "root" node - // unknown info, it won't be used anyway, in the future, - // we may want to enforce one element only (this is - // necessary for HTML Purifier to clean entire documents - $parent_index = $parent_name = $parent_def = null; - } - - // calculate context - if ($is_inline === false) { - // check if conditions make it inline - if (!empty($parent_def) && $parent_def->descendants_are_inline) { - $is_inline = $count - 1; - } - } else { - // check if we're out of inline - if ($count === $is_inline) { - $is_inline = false; - } - } - - //################################################################// - // Determine whether element is explicitly excluded SGML-style - - // determine whether or not element is excluded by checking all - // parent exclusions. The array should not be very large, two - // elements at most. - $excluded = false; - if (!empty($exclude_stack)) { - foreach ($exclude_stack as $lookup) { - if (isset($lookup[$tokens[$i]->name])) { - $excluded = true; - // no need to continue processing - break; - } + // We need to implement a post-order traversal iteratively, to + // avoid running into stack space limits. This is pretty tricky + // to reason about, so we just manually stack-ify the recursive + // variant: + // + // function f($node) { + // foreach ($node->children as $child) { + // f($child); + // } + // validate($node); + // } + // + // Thus, we will represent a stack frame as array($node, + // $is_inline, stack of children) + // e.g. array_reverse($node->children) - already processed + // children. + + $parent_def = $definition->info_parent_def; + $stack = array( + array($top_node, + $parent_def->descendants_are_inline, + $parent_def->excludes, // exclusions + 0) + ); + + while (!empty($stack)) { + list($node, $is_inline, $excludes, $ix) = array_pop($stack); + // recursive call + $go = false; + $def = empty($stack) ? $definition->info_parent_def : $definition->info[$node->name]; + while (isset($node->children[$ix])) { + $child = $node->children[$ix++]; + if ($child instanceof HTMLPurifier_Node_Element) { + $go = true; + $stack[] = array($node, $is_inline, $excludes, $ix); + $stack[] = array($child, + // ToDo: I don't think it matters if it's def or + // child_def, but double check this... + $is_inline || $def->descendants_are_inline, + empty($def->excludes) ? $excludes + : array_merge($excludes, $def->excludes), + 0); + break; } - } - - //################################################################// - // Perform child validation - - if ($excluded) { - // there is an exclusion, remove the entire node - $result = false; - $excludes = array(); // not used, but good to initialize anyway + }; + if ($go) continue; + list($token, $d) = $node->toTokenPair(); + // base case + if ($excludes_enabled && isset($excludes[$node->name])) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded'); } else { - // DEFINITION CALL - if ($i === 0) { - // special processing for the first node - $def = $definition->info_parent_def; - } else { - $def = $definition->info[$tokens[$i]->name]; - + // XXX I suppose it would be slightly more efficient to + // avoid the allocation here and have children + // strategies handle it + $children = array(); + foreach ($node->children as $child) { + if (!$child->dead) $children[] = $child; } - - if (!empty($def->child)) { - // have DTD child def validate children - $result = $def->child->validateChildren( - $child_tokens, $config, $context); + $result = $def->child->validateChildren($children, $config, $context); + if ($result === true) { + // nop + $node->children = $children; + } elseif ($result === false) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node removed'); } else { - // weird, no child definition, get rid of everything - $result = false; - } - - // determine whether or not this element has any exclusions - $excludes = $def->excludes; - } - - // $result is now a bool or array - - //################################################################// - // Process result by interpreting $result - - if ($result === true || $child_tokens === $result) { - // leave the node as is - - // register start token as a parental node start - $stack[] = $i; - - // register exclusions if there are any - if (!empty($excludes)) $exclude_stack[] = $excludes; - - // move cursor to next possible start node - $i++; - - } elseif($result === false) { - // remove entire node - - if ($e) { - if ($excluded) { - $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded'); - } else { - $e->send(E_ERROR, 'Strategy_FixNesting: Node removed'); - } - } - - // calculate length of inner tokens and current tokens - $length = $j - $i + 1; - - // perform removal - array_splice($tokens, $i, $length); - - // update size - $size -= $length; - - // there is no start token to register, - // current node is now the next possible start node - // unless it turns out that we need to do a double-check - - // this is a rought heuristic that covers 100% of HTML's - // cases and 99% of all other cases. A child definition - // that would be tricked by this would be something like: - // ( | a b c) where it's all or nothing. Fortunately, - // our current implementation claims that that case would - // not allow empty, even if it did - if (!$parent_def->child->allow_empty) { - // we need to do a double-check - $i = $parent_index; - array_pop($stack); - } - - // PROJECTED OPTIMIZATION: Process all children elements before - // reprocessing parent node. - - } else { - // replace node with $result - - // calculate length of inner tokens - $length = $j - $i - 1; - - if ($e) { - if (empty($result) && $length) { - $e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed'); - } else { - $e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized'); + $node->children = $result; + if ($e) { + // XXX This will miss mutations of internal nodes. Perhaps defer to the child validators + if (empty($result) && !empty($children)) { + $e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed'); + } else if ($result != $children) { + $e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized'); + } } } - - // perform replacement - array_splice($tokens, $i + 1, $length, $result); - - // update size - $size -= $length; - $size += count($result); - - // register start token as a parental node start - $stack[] = $i; - - // register exclusions if there are any - if (!empty($excludes)) $exclude_stack[] = $excludes; - - // move cursor to next possible start node - $i++; - } - - //################################################################// - // Scroll to next start node - - // We assume, at this point, that $i is the index of the token - // that is the first possible new start point for a node. - - // Test if the token indeed is a start tag, if not, move forward - // and test again. - $size = count($tokens); - while ($i < $size and !$tokens[$i] instanceof HTMLPurifier_Token_Start) { - if ($tokens[$i] instanceof HTMLPurifier_Token_End) { - // pop a token index off the stack if we ended a node - array_pop($stack); - // pop an exclusion lookup off exclusion stack if - // we ended node and that node had exclusions - if ($i == 0 || $i == $size - 1) { - // use specialized var if it's the super-parent - $s_excludes = $definition->info_parent_def->excludes; - } else { - $s_excludes = $definition->info[$tokens[$i]->name]->excludes; - } - if ($s_excludes) { - array_pop($exclude_stack); - } - } - $i++; - } - } //####################################################################// // Post-processing - // remove implicit parent tokens at the beginning and end - array_shift($tokens); - array_pop($tokens); - // remove context variables $context->destroy('IsInline'); + $context->destroy('CurrentNode'); $context->destroy('CurrentToken'); //####################################################################// // Return - return $tokens; - + return HTMLPurifier_Arborize::flatten($node, $config, $context); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Strategy/MakeWellFormed.php b/library/HTMLPurifier/Strategy/MakeWellFormed.php index c73658400..e389e0011 100644 --- a/library/HTMLPurifier/Strategy/MakeWellFormed.php +++ b/library/HTMLPurifier/Strategy/MakeWellFormed.php @@ -2,66 +2,97 @@ /** * Takes tokens makes them well-formed (balance end tags, etc.) + * + * Specification of the armor attributes this strategy uses: + * + * - MakeWellFormed_TagClosedError: This armor field is used to + * suppress tag closed errors for certain tokens [TagClosedSuppress], + * in particular, if a tag was generated automatically by HTML + * Purifier, we may rely on our infrastructure to close it for us + * and shouldn't report an error to the user [TagClosedAuto]. */ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy { /** * Array stream of tokens being processed. + * @type HTMLPurifier_Token[] */ protected $tokens; /** - * Current index in $tokens. + * Current token. + * @type HTMLPurifier_Token */ - protected $t; + protected $token; + + /** + * Zipper managing the true state. + * @type HTMLPurifier_Zipper + */ + protected $zipper; /** * Current nesting of elements. + * @type array */ protected $stack; /** * Injectors active in this stream processing. + * @type HTMLPurifier_Injector[] */ protected $injectors; /** * Current instance of HTMLPurifier_Config. + * @type HTMLPurifier_Config */ protected $config; /** * Current instance of HTMLPurifier_Context. + * @type HTMLPurifier_Context */ protected $context; - public function execute($tokens, $config, $context) { - + /** + * @param HTMLPurifier_Token[] $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] + * @throws HTMLPurifier_Exception + */ + public function execute($tokens, $config, $context) + { $definition = $config->getHTMLDefinition(); // local variables $generator = new HTMLPurifier_Generator($config, $context); $escape_invalid_tags = $config->get('Core.EscapeInvalidTags'); + // used for autoclose early abortion + $global_parent_allowed_elements = $definition->info_parent_def->child->getAllowedElements($config); $e = $context->get('ErrorCollector', true); - $t = false; // token index $i = false; // injector index - $token = false; // the current token - $reprocess = false; // whether or not to reprocess the same token + list($zipper, $token) = HTMLPurifier_Zipper::fromArray($tokens); + if ($token === NULL) { + return array(); + } + $reprocess = false; // whether or not to reprocess the same token $stack = array(); // member variables - $this->stack =& $stack; - $this->t =& $t; - $this->tokens =& $tokens; - $this->config = $config; + $this->stack =& $stack; + $this->tokens =& $tokens; + $this->token =& $token; + $this->zipper =& $zipper; + $this->config = $config; $this->context = $context; // context variables $context->register('CurrentNesting', $stack); - $context->register('InputIndex', $t); - $context->register('InputTokens', $tokens); - $context->register('CurrentToken', $token); + $context->register('InputZipper', $zipper); + $context->register('CurrentToken', $token); // -- begin INJECTOR -- @@ -73,9 +104,13 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy unset($injectors['Custom']); // special case foreach ($injectors as $injector => $b) { // XXX: Fix with a legitimate lookup table of enabled filters - if (strpos($injector, '.') !== false) continue; + if (strpos($injector, '.') !== false) { + continue; + } $injector = "HTMLPurifier_Injector_$injector"; - if (!$b) continue; + if (!$b) { + continue; + } $this->injectors[] = new $injector; } foreach ($def_injectors as $injector) { @@ -83,7 +118,9 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy $this->injectors[] = $injector; } foreach ($custom_injectors as $injector) { - if (!$injector) continue; + if (!$injector) { + continue; + } if (is_string($injector)) { $injector = "HTMLPurifier_Injector_$injector"; $injector = new $injector; @@ -95,14 +132,16 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy // variables for performance reasons foreach ($this->injectors as $ix => $injector) { $error = $injector->prepare($config, $context); - if (!$error) continue; + if (!$error) { + continue; + } array_splice($this->injectors, $ix, 1); // rm the injector trigger_error("Cannot enable {$injector->name} injector because $error is not allowed", E_USER_WARNING); } // -- end INJECTOR -- - // a note on punting: + // a note on reprocessing: // In order to reduce code duplication, whenever some code needs // to make HTML changes in order to make things "correct", the // new HTML gets sent through the purifier, regardless of its @@ -111,70 +150,75 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy // punt ($reprocess = true; continue;) and it does that for us. // isset is in loop because $tokens size changes during loop exec - for ( - $t = 0; - $t == 0 || isset($tokens[$t - 1]); - // only increment if we don't need to reprocess - $reprocess ? $reprocess = false : $t++ - ) { + for (;; + // only increment if we don't need to reprocess + $reprocess ? $reprocess = false : $token = $zipper->next($token)) { // check for a rewind - if (is_int($i) && $i >= 0) { + if (is_int($i)) { // possibility: disable rewinding if the current token has a // rewind set on it already. This would offer protection from // infinite loop, but might hinder some advanced rewinding. - $rewind_to = $this->injectors[$i]->getRewind(); - if (is_int($rewind_to) && $rewind_to < $t) { - if ($rewind_to < 0) $rewind_to = 0; - while ($t > $rewind_to) { - $t--; - $prev = $tokens[$t]; + $rewind_offset = $this->injectors[$i]->getRewindOffset(); + if (is_int($rewind_offset)) { + for ($j = 0; $j < $rewind_offset; $j++) { + if (empty($zipper->front)) break; + $token = $zipper->prev($token); // indicate that other injectors should not process this token, // but we need to reprocess it - unset($prev->skip[$i]); - $prev->rewind = $i; - if ($prev instanceof HTMLPurifier_Token_Start) array_pop($this->stack); - elseif ($prev instanceof HTMLPurifier_Token_End) $this->stack[] = $prev->start; + unset($token->skip[$i]); + $token->rewind = $i; + if ($token instanceof HTMLPurifier_Token_Start) { + array_pop($this->stack); + } elseif ($token instanceof HTMLPurifier_Token_End) { + $this->stack[] = $token->start; + } } } $i = false; } // handle case of document end - if (!isset($tokens[$t])) { + if ($token === NULL) { // kill processing if stack is empty - if (empty($this->stack)) break; + if (empty($this->stack)) { + break; + } // peek $top_nesting = array_pop($this->stack); $this->stack[] = $top_nesting; - // send error + // send error [TagClosedSuppress] if ($e && !isset($top_nesting->armor['MakeWellFormed_TagClosedError'])) { $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by document end', $top_nesting); } // append, don't splice, since this is the end - $tokens[] = new HTMLPurifier_Token_End($top_nesting->name); + $token = new HTMLPurifier_Token_End($top_nesting->name); // punt! $reprocess = true; continue; } - $token = $tokens[$t]; - - //echo '<br>'; printTokens($tokens, $t); printTokens($this->stack); + //echo '<br>'; printZipper($zipper, $token);//printTokens($this->stack); //flush(); // quick-check: if it's not a tag, no need to process if (empty($token->is_tag)) { if ($token instanceof HTMLPurifier_Token_Text) { foreach ($this->injectors as $i => $injector) { - if (isset($token->skip[$i])) continue; - if ($token->rewind !== null && $token->rewind !== $i) continue; - $injector->handleText($token); - $this->processToken($token, $i); + if (isset($token->skip[$i])) { + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + // XXX fuckup + $r = $token; + $injector->handleText($r); + $token = $this->processToken($r, $i); $reprocess = true; break; } @@ -193,12 +237,22 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy $ok = false; if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) { // claims to be a start tag but is empty - $token = new HTMLPurifier_Token_Empty($token->name, $token->attr); + $token = new HTMLPurifier_Token_Empty( + $token->name, + $token->attr, + $token->line, + $token->col, + $token->armor + ); $ok = true; } elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) { // claims to be empty but really is a start tag - $this->swap(new HTMLPurifier_Token_End($token->name)); - $this->insertBefore(new HTMLPurifier_Token_Start($token->name, $token->attr)); + // NB: this assignment is required + $old_token = $token; + $token = new HTMLPurifier_Token_End($token->name); + $token = $this->insertBefore( + new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_token->armor) + ); // punt (since we had to modify the input stream in a non-trivial way) $reprocess = true; continue; @@ -211,55 +265,96 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy // ...unless they also have to close their parent if (!empty($this->stack)) { + // Performance note: you might think that it's rather + // inefficient, recalculating the autoclose information + // for every tag that a token closes (since when we + // do an autoclose, we push a new token into the + // stream and then /process/ that, before + // re-processing this token.) But this is + // necessary, because an injector can make an + // arbitrary transformations to the autoclosing + // tokens we introduce, so things may have changed + // in the meantime. Also, doing the inefficient thing is + // "easy" to reason about (for certain perverse definitions + // of "easy") + $parent = array_pop($this->stack); $this->stack[] = $parent; + $parent_def = null; + $parent_elements = null; + $autoclose = false; if (isset($definition->info[$parent->name])) { - $elements = $definition->info[$parent->name]->child->getAllowedElements($config); - $autoclose = !isset($elements[$token->name]); - } else { - $autoclose = false; + $parent_def = $definition->info[$parent->name]; + $parent_elements = $parent_def->child->getAllowedElements($config); + $autoclose = !isset($parent_elements[$token->name]); } if ($autoclose && $definition->info[$token->name]->wrap) { - // Check if an element can be wrapped by another - // element to make it valid in a context (for + // Check if an element can be wrapped by another + // element to make it valid in a context (for // example, <ul><ul> needs a <li> in between) $wrapname = $definition->info[$token->name]->wrap; $wrapdef = $definition->info[$wrapname]; $elements = $wrapdef->child->getAllowedElements($config); - $parent_elements = $definition->info[$parent->name]->child->getAllowedElements($config); if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) { $newtoken = new HTMLPurifier_Token_Start($wrapname); - $this->insertBefore($newtoken); + $token = $this->insertBefore($newtoken); $reprocess = true; continue; } } $carryover = false; - if ($autoclose && $definition->info[$parent->name]->formatting) { + if ($autoclose && $parent_def->formatting) { $carryover = true; } if ($autoclose) { - // errors need to be updated - $new_token = new HTMLPurifier_Token_End($parent->name); - $new_token->start = $parent; - if ($carryover) { - $element = clone $parent; - $element->armor['MakeWellFormed_TagClosedError'] = true; - $element->carryover = true; - $this->processToken(array($new_token, $token, $element)); - } else { - $this->insertBefore($new_token); + // check if this autoclose is doomed to fail + // (this rechecks $parent, which his harmless) + $autoclose_ok = isset($global_parent_allowed_elements[$token->name]); + if (!$autoclose_ok) { + foreach ($this->stack as $ancestor) { + $elements = $definition->info[$ancestor->name]->child->getAllowedElements($config); + if (isset($elements[$token->name])) { + $autoclose_ok = true; + break; + } + if ($definition->info[$token->name]->wrap) { + $wrapname = $definition->info[$token->name]->wrap; + $wrapdef = $definition->info[$wrapname]; + $wrap_elements = $wrapdef->child->getAllowedElements($config); + if (isset($wrap_elements[$token->name]) && isset($elements[$wrapname])) { + $autoclose_ok = true; + break; + } + } + } } - if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) { - if (!$carryover) { - $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent); + if ($autoclose_ok) { + // errors need to be updated + $new_token = new HTMLPurifier_Token_End($parent->name); + $new_token->start = $parent; + // [TagClosedSuppress] + if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) { + if (!$carryover) { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent); + } else { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent); + } + } + if ($carryover) { + $element = clone $parent; + // [TagClosedAuto] + $element->armor['MakeWellFormed_TagClosedError'] = true; + $element->carryover = true; + $token = $this->processToken(array($new_token, $token, $element)); } else { - $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent); + $token = $this->insertBefore($new_token); } + } else { + $token = $this->remove(); } $reprocess = true; continue; @@ -271,20 +366,26 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy if ($ok) { foreach ($this->injectors as $i => $injector) { - if (isset($token->skip[$i])) continue; - if ($token->rewind !== null && $token->rewind !== $i) continue; - $injector->handleElement($token); - $this->processToken($token, $i); + if (isset($token->skip[$i])) { + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + $r = $token; + $injector->handleElement($r); + $token = $this->processToken($r, $i); $reprocess = true; break; } if (!$reprocess) { // ah, nothing interesting happened; do normal processing - $this->swap($token); if ($token instanceof HTMLPurifier_Token_Start) { $this->stack[] = $token; } elseif ($token instanceof HTMLPurifier_Token_End) { - throw new HTMLPurifier_Exception('Improper handling of end tag in start code; possible error in MakeWellFormed'); + throw new HTMLPurifier_Exception( + 'Improper handling of end tag in start code; possible error in MakeWellFormed' + ); } } continue; @@ -298,13 +399,15 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy // make sure that we have something open if (empty($this->stack)) { if ($escape_invalid_tags) { - if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text'); - $this->swap(new HTMLPurifier_Token_Text( - $generator->generateFromToken($token) - )); + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); } else { - $this->remove(); - if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed'); + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed'); + } + $token = $this->remove(); } $reprocess = true; continue; @@ -318,10 +421,15 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy if ($current_parent->name == $token->name) { $token->start = $current_parent; foreach ($this->injectors as $i => $injector) { - if (isset($token->skip[$i])) continue; - if ($token->rewind !== null && $token->rewind !== $i) continue; - $injector->handleEnd($token); - $this->processToken($token, $i); + if (isset($token->skip[$i])) { + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + $r = $token; + $injector->handleEnd($r); + $token = $this->processToken($r, $i); $this->stack[] = $current_parent; $reprocess = true; break; @@ -349,13 +457,15 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy // we didn't find the tag, so remove if ($skipped_tags === false) { if ($escape_invalid_tags) { - $this->swap(new HTMLPurifier_Token_Text( - $generator->generateFromToken($token) - )); - if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text'); + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); } else { - $this->remove(); - if ($e) $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed'); + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed'); + } + $token = $this->remove(); } $reprocess = true; continue; @@ -366,7 +476,7 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy if ($e) { for ($j = $c - 1; $j > 0; $j--) { // notice we exclude $j == 0, i.e. the current ending tag, from - // the errors... + // the errors... [TagClosedSuppress] if (!isset($skipped_tags[$j]->armor['MakeWellFormed_TagClosedError'])) { $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by element end', $skipped_tags[$j]); } @@ -381,24 +491,24 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy $new_token->start = $skipped_tags[$j]; array_unshift($replace, $new_token); if (isset($definition->info[$new_token->name]) && $definition->info[$new_token->name]->formatting) { + // [TagClosedAuto] $element = clone $skipped_tags[$j]; $element->carryover = true; $element->armor['MakeWellFormed_TagClosedError'] = true; $replace[] = $element; } } - $this->processToken($replace); + $token = $this->processToken($replace); $reprocess = true; continue; } - $context->destroy('CurrentNesting'); - $context->destroy('InputTokens'); - $context->destroy('InputIndex'); $context->destroy('CurrentToken'); + $context->destroy('CurrentNesting'); + $context->destroy('InputZipper'); - unset($this->injectors, $this->stack, $this->tokens, $this->t); - return $tokens; + unset($this->injectors, $this->stack, $this->tokens); + return $zipper->toArray($token); } /** @@ -417,25 +527,38 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy * If $token is an integer, that number of tokens (with the first token * being the current one) will be deleted. * - * @param $token Token substitution value - * @param $injector Injector that performed the substitution; default is if + * @param HTMLPurifier_Token|array|int|bool $token Token substitution value + * @param HTMLPurifier_Injector|int $injector Injector that performed the substitution; default is if * this is not an injector related operation. + * @throws HTMLPurifier_Exception */ - protected function processToken($token, $injector = -1) { - + protected function processToken($token, $injector = -1) + { // normalize forms of token - if (is_object($token)) $token = array(1, $token); - if (is_int($token)) $token = array($token); - if ($token === false) $token = array(1); - if (!is_array($token)) throw new HTMLPurifier_Exception('Invalid token type from injector'); - if (!is_int($token[0])) array_unshift($token, 1); - if ($token[0] === 0) throw new HTMLPurifier_Exception('Deleting zero tokens is not valid'); + if (is_object($token)) { + $token = array(1, $token); + } + if (is_int($token)) { + $token = array($token); + } + if ($token === false) { + $token = array(1); + } + if (!is_array($token)) { + throw new HTMLPurifier_Exception('Invalid token type from injector'); + } + if (!is_int($token[0])) { + array_unshift($token, 1); + } + if ($token[0] === 0) { + throw new HTMLPurifier_Exception('Deleting zero tokens is not valid'); + } // $token is now an array with the following form: // array(number nodes to delete, new node 1, new node 2, ...) $delete = array_shift($token); - $old = array_splice($this->tokens, $this->t, $delete, $token); + list($old, $r) = $this->zipper->splice($this->token, $delete, $token); if ($injector > -1) { // determine appropriate skips @@ -446,30 +569,32 @@ class HTMLPurifier_Strategy_MakeWellFormed extends HTMLPurifier_Strategy } } - } + return $r; - /** - * Inserts a token before the current token. Cursor now points to this token - */ - private function insertBefore($token) { - array_splice($this->tokens, $this->t, 0, array($token)); } /** - * Removes current token. Cursor now points to new token occupying previously - * occupied space. + * Inserts a token before the current token. Cursor now points to + * this token. You must reprocess after this. + * @param HTMLPurifier_Token $token */ - private function remove() { - array_splice($this->tokens, $this->t, 1); + private function insertBefore($token) + { + // NB not $this->zipper->insertBefore(), due to positioning + // differences + $splice = $this->zipper->splice($this->token, 0, array($token)); + + return $splice[1]; } /** - * Swap current token with new token. Cursor points to new token (no change). + * Removes current token. Cursor now points to new token occupying previously + * occupied space. You must reprocess after this. */ - private function swap($token) { - $this->tokens[$this->t] = $token; + private function remove() + { + return $this->zipper->delete(); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Strategy/RemoveForeignElements.php b/library/HTMLPurifier/Strategy/RemoveForeignElements.php index cf3a33e40..1a8149ecc 100644 --- a/library/HTMLPurifier/Strategy/RemoveForeignElements.php +++ b/library/HTMLPurifier/Strategy/RemoveForeignElements.php @@ -11,19 +11,29 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy { - public function execute($tokens, $config, $context) { + /** + * @param HTMLPurifier_Token[] $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array|HTMLPurifier_Token[] + */ + public function execute($tokens, $config, $context) + { $definition = $config->getHTMLDefinition(); $generator = new HTMLPurifier_Generator($config, $context); $result = array(); $escape_invalid_tags = $config->get('Core.EscapeInvalidTags'); - $remove_invalid_img = $config->get('Core.RemoveInvalidImg'); + $remove_invalid_img = $config->get('Core.RemoveInvalidImg'); // currently only used to determine if comments should be kept $trusted = $config->get('HTML.Trusted'); + $comment_lookup = $config->get('HTML.AllowedComments'); + $comment_regexp = $config->get('HTML.AllowedCommentsRegexp'); + $check_comments = $comment_lookup !== array() || $comment_regexp !== null; $remove_script_contents = $config->get('Core.RemoveScriptContents'); - $hidden_elements = $config->get('Core.HiddenElements'); + $hidden_elements = $config->get('Core.HiddenElements'); // remove script contents compatibility if ($remove_script_contents === true) { @@ -48,34 +58,31 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy $e =& $context->get('ErrorCollector'); } - foreach($tokens as $token) { + foreach ($tokens as $token) { if ($remove_until) { if (empty($token->is_tag) || $token->name !== $remove_until) { continue; } } - if (!empty( $token->is_tag )) { + if (!empty($token->is_tag)) { // DEFINITION CALL // before any processing, try to transform the element - if ( - isset($definition->info_tag_transform[$token->name]) - ) { + if (isset($definition->info_tag_transform[$token->name])) { $original_name = $token->name; // there is a transformation for this tag // DEFINITION CALL $token = $definition-> - info_tag_transform[$token->name]-> - transform($token, $config, $context); - if ($e) $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Tag transform', $original_name); + info_tag_transform[$token->name]->transform($token, $config, $context); + if ($e) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Tag transform', $original_name); + } } if (isset($definition->info[$token->name])) { - // mostly everything's good, but // we need to make sure required attributes are in order - if ( - ($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) && + if (($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) && $definition->info[$token->name]->required_attr && ($token->name != 'img' || $remove_invalid_img) // ensure config option still works ) { @@ -88,7 +95,13 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy } } if (!$ok) { - if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Missing required attribute', $name); + if ($e) { + $e->send( + E_ERROR, + 'Strategy_RemoveForeignElements: Missing required attribute', + $name + ); + } continue; } $token->armor['ValidateAttributes'] = true; @@ -102,7 +115,9 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy } elseif ($escape_invalid_tags) { // invalid tag, generate HTML representation and insert in - if ($e) $e->send(E_WARNING, 'Strategy_RemoveForeignElements: Foreign element to text'); + if ($e) { + $e->send(E_WARNING, 'Strategy_RemoveForeignElements: Foreign element to text'); + } $token = new HTMLPurifier_Token_Text( $generator->generateFromToken($token) ); @@ -117,9 +132,13 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy } else { $remove_until = false; } - if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign meta element removed'); + if ($e) { + $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign meta element removed'); + } } else { - if ($e) $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign element removed'); + if ($e) { + $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign element removed'); + } } continue; } @@ -128,26 +147,46 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy if ($textify_comments !== false) { $data = $token->data; $token = new HTMLPurifier_Token_Text($data); - } elseif ($trusted) { - // keep, but perform comment cleaning + } elseif ($trusted || $check_comments) { + // always cleanup comments + $trailing_hyphen = false; if ($e) { // perform check whether or not there's a trailing hyphen if (substr($token->data, -1) == '-') { - $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed'); + $trailing_hyphen = true; } } $token->data = rtrim($token->data, '-'); $found_double_hyphen = false; while (strpos($token->data, '--') !== false) { - if ($e && !$found_double_hyphen) { - $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Hyphens in comment collapsed'); - } - $found_double_hyphen = true; // prevent double-erroring + $found_double_hyphen = true; $token->data = str_replace('--', '-', $token->data); } + if ($trusted || !empty($comment_lookup[trim($token->data)]) || + ($comment_regexp !== null && preg_match($comment_regexp, trim($token->data)))) { + // OK good + if ($e) { + if ($trailing_hyphen) { + $e->send( + E_NOTICE, + 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' + ); + } + if ($found_double_hyphen) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Hyphens in comment collapsed'); + } + } + } else { + if ($e) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed'); + } + continue; + } } else { // strip comments - if ($e) $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed'); + if ($e) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed'); + } continue; } } elseif ($token instanceof HTMLPurifier_Token_Text) { @@ -160,12 +199,9 @@ class HTMLPurifier_Strategy_RemoveForeignElements extends HTMLPurifier_Strategy // we removed tokens until the end, throw error $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Token removed to end', $remove_until); } - $context->destroy('CurrentToken'); - return $result; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Strategy/ValidateAttributes.php b/library/HTMLPurifier/Strategy/ValidateAttributes.php index c3328a9d4..fbb3d27c8 100644 --- a/library/HTMLPurifier/Strategy/ValidateAttributes.php +++ b/library/HTMLPurifier/Strategy/ValidateAttributes.php @@ -7,8 +7,14 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy { - public function execute($tokens, $config, $context) { - + /** + * @param HTMLPurifier_Token[] $tokens + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] + */ + public function execute($tokens, $config, $context) + { // setup validator $validator = new HTMLPurifier_AttrValidator(); @@ -19,21 +25,21 @@ class HTMLPurifier_Strategy_ValidateAttributes extends HTMLPurifier_Strategy // only process tokens that have attributes, // namely start and empty tags - if (!$token instanceof HTMLPurifier_Token_Start && !$token instanceof HTMLPurifier_Token_Empty) continue; + if (!$token instanceof HTMLPurifier_Token_Start && !$token instanceof HTMLPurifier_Token_Empty) { + continue; + } // skip tokens that are armored - if (!empty($token->armor['ValidateAttributes'])) continue; + if (!empty($token->armor['ValidateAttributes'])) { + continue; + } // note that we have no facilities here for removing tokens $validator->validateToken($token, $config, $context); - - $tokens[$key] = $token; // for PHP 4 } $context->destroy('CurrentToken'); - return $tokens; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/StringHash.php b/library/HTMLPurifier/StringHash.php index 62085c5c2..c07370197 100644 --- a/library/HTMLPurifier/StringHash.php +++ b/library/HTMLPurifier/StringHash.php @@ -10,28 +10,36 @@ */ class HTMLPurifier_StringHash extends ArrayObject { + /** + * @type array + */ protected $accessed = array(); /** * Retrieves a value, and logs the access. + * @param mixed $index + * @return mixed */ - public function offsetGet($index) { + public function offsetGet($index) + { $this->accessed[$index] = true; return parent::offsetGet($index); } /** * Returns a lookup array of all array indexes that have been accessed. - * @return Array in form array($index => true). + * @return array in form array($index => true). */ - public function getAccessed() { + public function getAccessed() + { return $this->accessed; } /** * Resets the access array. */ - public function resetAccessed() { + public function resetAccessed() + { $this->accessed = array(); } } diff --git a/library/HTMLPurifier/StringHashParser.php b/library/HTMLPurifier/StringHashParser.php index f3e70c712..7c73f8083 100644 --- a/library/HTMLPurifier/StringHashParser.php +++ b/library/HTMLPurifier/StringHashParser.php @@ -28,15 +28,25 @@ class HTMLPurifier_StringHashParser { + /** + * @type string + */ public $default = 'ID'; /** * Parses a file that contains a single string-hash. + * @param string $file + * @return array */ - public function parseFile($file) { - if (!file_exists($file)) return false; + public function parseFile($file) + { + if (!file_exists($file)) { + return false; + } $fh = fopen($file, 'r'); - if (!$fh) return false; + if (!$fh) { + return false; + } $ret = $this->parseHandle($fh); fclose($fh); return $ret; @@ -44,12 +54,19 @@ class HTMLPurifier_StringHashParser /** * Parses a file that contains multiple string-hashes delimited by '----' + * @param string $file + * @return array */ - public function parseMultiFile($file) { - if (!file_exists($file)) return false; + public function parseMultiFile($file) + { + if (!file_exists($file)) { + return false; + } $ret = array(); $fh = fopen($file, 'r'); - if (!$fh) return false; + if (!$fh) { + return false; + } while (!feof($fh)) { $ret[] = $this->parseHandle($fh); } @@ -62,26 +79,36 @@ class HTMLPurifier_StringHashParser * @note While it's possible to simulate in-memory parsing by using * custom stream wrappers, if such a use-case arises we should * factor out the file handle into its own class. - * @param $fh File handle with pointer at start of valid string-hash + * @param resource $fh File handle with pointer at start of valid string-hash * block. + * @return array */ - protected function parseHandle($fh) { + protected function parseHandle($fh) + { $state = false; $single = false; $ret = array(); do { $line = fgets($fh); - if ($line === false) break; + if ($line === false) { + break; + } $line = rtrim($line, "\n\r"); - if (!$state && $line === '') continue; - if ($line === '----') break; + if (!$state && $line === '') { + continue; + } + if ($line === '----') { + break; + } if (strncmp('--#', $line, 3) === 0) { // Comment continue; } elseif (strncmp('--', $line, 2) === 0) { // Multiline declaration $state = trim($line, '- '); - if (!isset($ret[$state])) $ret[$state] = ''; + if (!isset($ret[$state])) { + $ret[$state] = ''; + } continue; } elseif (!$state) { $single = true; @@ -104,7 +131,6 @@ class HTMLPurifier_StringHashParser } while (!feof($fh)); return $ret; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/TagTransform.php b/library/HTMLPurifier/TagTransform.php index 210a44721..7b8d83343 100644 --- a/library/HTMLPurifier/TagTransform.php +++ b/library/HTMLPurifier/TagTransform.php @@ -8,14 +8,15 @@ abstract class HTMLPurifier_TagTransform /** * Tag name to transform the tag to. + * @type string */ public $transform_to; /** * Transforms the obsolete tag into the valid tag. - * @param $tag Tag to be transformed. - * @param $config Mandatory HTMLPurifier_Config object - * @param $context Mandatory HTMLPurifier_Context object + * @param HTMLPurifier_Token_Tag $tag Tag to be transformed. + * @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object + * @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object */ abstract public function transform($tag, $config, $context); @@ -23,14 +24,14 @@ abstract class HTMLPurifier_TagTransform * Prepends CSS properties to the style attribute, creating the * attribute if it doesn't exist. * @warning Copied over from AttrTransform, be sure to keep in sync - * @param $attr Attribute array to process (passed by reference) - * @param $css CSS to prepend + * @param array $attr Attribute array to process (passed by reference) + * @param string $css CSS to prepend */ - protected function prependCSS(&$attr, $css) { + protected function prependCSS(&$attr, $css) + { $attr['style'] = isset($attr['style']) ? $attr['style'] : ''; $attr['style'] = $css . $attr['style']; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/TagTransform/Font.php b/library/HTMLPurifier/TagTransform/Font.php index ed2463786..7853d90bc 100644 --- a/library/HTMLPurifier/TagTransform/Font.php +++ b/library/HTMLPurifier/TagTransform/Font.php @@ -17,9 +17,14 @@ */ class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform { - + /** + * @type string + */ public $transform_to = 'span'; + /** + * @type array + */ protected $_size_lookup = array( '0' => 'xx-small', '1' => 'xx-small', @@ -37,8 +42,14 @@ class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform '+4' => '300%' ); - public function transform($tag, $config, $context) { - + /** + * @param HTMLPurifier_Token_Tag $tag + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token_End|string + */ + public function transform($tag, $config, $context) + { if ($tag instanceof HTMLPurifier_Token_End) { $new_tag = clone $tag; $new_tag->name = $this->transform_to; @@ -63,17 +74,25 @@ class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform // handle size transform if (isset($attr['size'])) { // normalize large numbers - if ($attr['size']{0} == '+' || $attr['size']{0} == '-') { - $size = (int) $attr['size']; - if ($size < -2) $attr['size'] = '-2'; - if ($size > 4) $attr['size'] = '+4'; - } else { - $size = (int) $attr['size']; - if ($size > 7) $attr['size'] = '7'; + if ($attr['size'] !== '') { + if ($attr['size']{0} == '+' || $attr['size']{0} == '-') { + $size = (int)$attr['size']; + if ($size < -2) { + $attr['size'] = '-2'; + } + if ($size > 4) { + $attr['size'] = '+4'; + } + } else { + $size = (int)$attr['size']; + if ($size > 7) { + $attr['size'] = '7'; + } + } } if (isset($this->_size_lookup[$attr['size']])) { $prepend_style .= 'font-size:' . - $this->_size_lookup[$attr['size']] . ';'; + $this->_size_lookup[$attr['size']] . ';'; } unset($attr['size']); } @@ -89,7 +108,6 @@ class HTMLPurifier_TagTransform_Font extends HTMLPurifier_TagTransform $new_tag->attr = $attr; return $new_tag; - } } diff --git a/library/HTMLPurifier/TagTransform/Simple.php b/library/HTMLPurifier/TagTransform/Simple.php index 0e36130f2..71bf10b91 100644 --- a/library/HTMLPurifier/TagTransform/Simple.php +++ b/library/HTMLPurifier/TagTransform/Simple.php @@ -7,19 +7,29 @@ */ class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform { - + /** + * @type string + */ protected $style; /** - * @param $transform_to Tag name to transform to. - * @param $style CSS style to add to the tag + * @param string $transform_to Tag name to transform to. + * @param string $style CSS style to add to the tag */ - public function __construct($transform_to, $style = null) { + public function __construct($transform_to, $style = null) + { $this->transform_to = $transform_to; $this->style = $style; } - public function transform($tag, $config, $context) { + /** + * @param HTMLPurifier_Token_Tag $tag + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function transform($tag, $config, $context) + { $new_tag = clone $tag; $new_tag->name = $this->transform_to; if (!is_null($this->style) && @@ -29,7 +39,6 @@ class HTMLPurifier_TagTransform_Simple extends HTMLPurifier_TagTransform } return $new_tag; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Token.php b/library/HTMLPurifier/Token.php index 7900e6cb1..85b85e072 100644 --- a/library/HTMLPurifier/Token.php +++ b/library/HTMLPurifier/Token.php @@ -3,55 +3,98 @@ /** * Abstract base token class that all others inherit from. */ -class HTMLPurifier_Token { - public $line; /**< Line number node was on in source document. Null if unknown. */ - public $col; /**< Column of line node was on in source document. Null if unknown. */ +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. + * @type */ public $skip; + + /** + * @type + */ public $rewind; + + /** + * @type + */ public $carryover; - public function __get($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; + /** + * @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, $c = null) { + public function position($l = null, $c = null) + { $this->line = $l; - $this->col = $c; + $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) $l++; + public function rawPosition($l, $c) + { + if ($c === -1) { + $l++; + } $this->line = $l; - $this->col = $c; + $this->col = $c; } + /** + * Converts a token into its corresponding node. + */ + abstract public function toNode(); } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Token/Comment.php b/library/HTMLPurifier/Token/Comment.php index dc6bdcabb..23453c705 100644 --- a/library/HTMLPurifier/Token/Comment.php +++ b/library/HTMLPurifier/Token/Comment.php @@ -5,17 +5,33 @@ */ class HTMLPurifier_Token_Comment extends HTMLPurifier_Token { - public $data; /**< Character data within comment. */ + /** + * Character data within comment. + * @type string + */ + public $data; + + /** + * @type bool + */ public $is_whitespace = true; + /** * Transparent constructor. * - * @param $data String comment data. + * @param string $data String comment data. + * @param int $line + * @param int $col */ - public function __construct($data, $line = null, $col = null) { + public function __construct($data, $line = null, $col = null) + { $this->data = $data; $this->line = $line; - $this->col = $col; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Comment($this->data, $this->line, $this->col); } } diff --git a/library/HTMLPurifier/Token/Empty.php b/library/HTMLPurifier/Token/Empty.php index 2a82b47ad..78a95f555 100644 --- a/library/HTMLPurifier/Token/Empty.php +++ b/library/HTMLPurifier/Token/Empty.php @@ -5,7 +5,11 @@ */ 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/HTMLPurifier/Token/End.php b/library/HTMLPurifier/Token/End.php index 353e79daf..59b38fdc5 100644 --- a/library/HTMLPurifier/Token/End.php +++ b/library/HTMLPurifier/Token/End.php @@ -10,10 +10,15 @@ class HTMLPurifier_Token_End extends HTMLPurifier_Token_Tag { /** - * Token that started this node. Added by MakeWellFormed. Please - * do not edit this! + * Token that started this node. + * Added by MakeWellFormed. Please do not edit this! + * @type HTMLPurifier_Token */ public $start; + + public function toNode() { + throw new Exception("HTMLPurifier_Token_End->toNode not supported!"); + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Token/Start.php b/library/HTMLPurifier/Token/Start.php index e0e14fc62..019f317ad 100644 --- a/library/HTMLPurifier/Token/Start.php +++ b/library/HTMLPurifier/Token/Start.php @@ -5,7 +5,6 @@ */ class HTMLPurifier_Token_Start extends HTMLPurifier_Token_Tag { - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Token/Tag.php b/library/HTMLPurifier/Token/Tag.php index 798be028e..d643fa64e 100644 --- a/library/HTMLPurifier/Token/Tag.php +++ b/library/HTMLPurifier/Token/Tag.php @@ -3,13 +3,14 @@ /** * Abstract class of a tag token (start, end or empty), and its behavior. */ -class HTMLPurifier_Token_Tag extends HTMLPurifier_Token +abstract class HTMLPurifier_Token_Tag extends HTMLPurifier_Token { /** * Static bool marker that indicates the class is a tag. * * This allows us to check objects with <tt>!empty($obj->is_tag)</tt> * without having to use a function call <tt>is_a()</tt>. + * @type bool */ public $is_tag = true; @@ -19,21 +20,27 @@ class HTMLPurifier_Token_Tag extends HTMLPurifier_Token * @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 $name String name. - * @param $attr Associative array of attributes. + * @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, $col = null) { + public function __construct($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 @@ -49,7 +56,12 @@ class HTMLPurifier_Token_Tag extends HTMLPurifier_Token } $this->attr = $attr; $this->line = $line; - $this->col = $col; + $this->col = $col; + $this->armor = $armor; + } + + public function toNode() { + return new HTMLPurifier_Node_Element($this->name, $this->attr, $this->line, $this->col, $this->armor); } } diff --git a/library/HTMLPurifier/Token/Text.php b/library/HTMLPurifier/Token/Text.php index 82efd823d..f26a1c211 100644 --- a/library/HTMLPurifier/Token/Text.php +++ b/library/HTMLPurifier/Token/Text.php @@ -12,22 +12,42 @@ class HTMLPurifier_Token_Text extends HTMLPurifier_Token { - public $name = '#PCDATA'; /**< PCDATA tag name compatible with DTD. */ - public $data; /**< Parsed character data of text. */ - public $is_whitespace; /**< Bool indicating if node is whitespace. */ + /** + * @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 $data String parsed character data. + * @param string $data String parsed character data. + * @param int $line + * @param int $col */ - public function __construct($data, $line = null, $col = null) { + public function __construct($data, $line = null, $col = null) + { $this->data = $data; $this->is_whitespace = ctype_space($data); $this->line = $line; - $this->col = $col; + $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/HTMLPurifier/TokenFactory.php b/library/HTMLPurifier/TokenFactory.php index 7cf48fb41..dea2446b9 100644 --- a/library/HTMLPurifier/TokenFactory.php +++ b/library/HTMLPurifier/TokenFactory.php @@ -13,32 +13,53 @@ */ class HTMLPurifier_TokenFactory { + // p stands for prototype /** - * Prototypes that will be cloned. - * @private + * @type HTMLPurifier_Token_Start */ - // p stands for prototype - private $p_start, $p_end, $p_empty, $p_text, $p_comment; + 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(''); + 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 $name Tag name - * @param $attr Associative array of attributes - * @return Generated 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, $attr = array()) { + public function createStart($name, $attr = array()) + { $p = clone $this->p_start; $p->__construct($name, $attr); return $p; @@ -46,10 +67,11 @@ class HTMLPurifier_TokenFactory /** * Creates a HTMLPurifier_Token_End. - * @param $name Tag name - * @return Generated HTMLPurifier_Token_End + * @param string $name Tag name + * @return HTMLPurifier_Token_End Generated HTMLPurifier_Token_End */ - public function createEnd($name) { + public function createEnd($name) + { $p = clone $this->p_end; $p->__construct($name); return $p; @@ -57,11 +79,12 @@ class HTMLPurifier_TokenFactory /** * Creates a HTMLPurifier_Token_Empty. - * @param $name Tag name - * @param $attr Associative array of attributes - * @return Generated 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, $attr = array()) { + public function createEmpty($name, $attr = array()) + { $p = clone $this->p_empty; $p->__construct($name, $attr); return $p; @@ -69,10 +92,11 @@ class HTMLPurifier_TokenFactory /** * Creates a HTMLPurifier_Token_Text. - * @param $data Data of text token - * @return Generated HTMLPurifier_Token_Text + * @param string $data Data of text token + * @return HTMLPurifier_Token_Text Generated HTMLPurifier_Token_Text */ - public function createText($data) { + public function createText($data) + { $p = clone $this->p_text; $p->__construct($data); return $p; @@ -80,15 +104,15 @@ class HTMLPurifier_TokenFactory /** * Creates a HTMLPurifier_Token_Comment. - * @param $data Data of comment token - * @return Generated HTMLPurifier_Token_Comment + * @param string $data Data of comment token + * @return HTMLPurifier_Token_Comment Generated HTMLPurifier_Token_Comment */ - public function createComment($data) { + public function createComment($data) + { $p = clone $this->p_comment; $p->__construct($data); return $p; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URI.php b/library/HTMLPurifier/URI.php index 8b50d0d18..a5e7ae298 100644 --- a/library/HTMLPurifier/URI.php +++ b/library/HTMLPurifier/URI.php @@ -10,17 +10,57 @@ */ class HTMLPurifier_URI { + /** + * @type string + */ + public $scheme; - public $scheme, $userinfo, $host, $port, $path, $query, $fragment; + /** + * @type string + */ + public $userinfo; /** + * @type string + */ + public $host; + + /** + * @type int + */ + public $port; + + /** + * @type string + */ + public $path; + + /** + * @type string + */ + public $query; + + /** + * @type string + */ + public $fragment; + + /** + * @param string $scheme + * @param string $userinfo + * @param string $host + * @param int $port + * @param string $path + * @param string $query + * @param string $fragment * @note Automatically normalizes scheme and port */ - public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) { + public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) + { $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme); $this->userinfo = $userinfo; $this->host = $host; - $this->port = is_null($port) ? $port : (int) $port; + $this->port = is_null($port) ? $port : (int)$port; $this->path = $path; $this->query = $query; $this->fragment = $fragment; @@ -28,19 +68,22 @@ class HTMLPurifier_URI /** * Retrieves a scheme object corresponding to the URI's scheme/default - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @return Scheme object appropriate for validating this URI + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_URIScheme Scheme object appropriate for validating this URI */ - public function getSchemeObj($config, $context) { + public function getSchemeObj($config, $context) + { $registry = HTMLPurifier_URISchemeRegistry::instance(); if ($this->scheme !== null) { $scheme_obj = $registry->getScheme($this->scheme, $config, $context); - if (!$scheme_obj) return false; // invalid scheme, clean it out + if (!$scheme_obj) { + return false; + } // invalid scheme, clean it out } else { // no scheme: retrieve the default one $def = $config->getDefinition('URI'); - $scheme_obj = $registry->getScheme($def->defaultScheme, $config, $context); + $scheme_obj = $def->getDefaultScheme($config, $context); if (!$scheme_obj) { // something funky happened to the default scheme object trigger_error( @@ -56,30 +99,39 @@ class HTMLPurifier_URI /** * Generic validation method applicable for all schemes. May modify * this URI in order to get it into a compliant form. - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context - * @return True if validation/filtering succeeds, false if failure + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool True if validation/filtering succeeds, false if failure */ - public function validate($config, $context) { - + public function validate($config, $context) + { // ABNF definitions from RFC 3986 $chars_sub_delims = '!$&\'()*+,;='; $chars_gen_delims = ':/?#[]@'; $chars_pchar = $chars_sub_delims . ':@'; - // validate scheme (MUST BE FIRST!) - if (!is_null($this->scheme) && is_null($this->host)) { - $def = $config->getDefinition('URI'); - if ($def->defaultScheme === $this->scheme) { - $this->scheme = null; - } - } - // validate host if (!is_null($this->host)) { $host_def = new HTMLPurifier_AttrDef_URI_Host(); $this->host = $host_def->validate($this->host, $config, $context); - if ($this->host === false) $this->host = null; + if ($this->host === false) { + $this->host = null; + } + } + + // validate scheme + // NOTE: It's not appropriate to check whether or not this + // scheme is in our registry, since a URIFilter may convert a + // URI that we don't allow into one we do. So instead, we just + // check if the scheme can be dropped because there is no host + // and it is our default scheme. + if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') { + // support for relative paths is pretty abysmal when the + // scheme is present, so axe it when possible + $def = $config->getDefinition('URI'); + if ($def->defaultScheme === $this->scheme) { + $this->scheme = null; + } } // validate username @@ -90,38 +142,55 @@ class HTMLPurifier_URI // validate port if (!is_null($this->port)) { - if ($this->port < 1 || $this->port > 65535) $this->port = null; + if ($this->port < 1 || $this->port > 65535) { + $this->port = null; + } } // validate path - $path_parts = array(); $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/'); - if (!is_null($this->host)) { + if (!is_null($this->host)) { // this catches $this->host === '' // path-abempty (hier and relative) + // http://www.example.com/my/path + // //www.example.com/my/path (looks odd, but works, and + // recognized by most browsers) + // (this set is valid or invalid on a scheme by scheme + // basis, so we'll deal with it later) + // file:///my/path + // ///my/path $this->path = $segments_encoder->encode($this->path); - } elseif ($this->path !== '' && $this->path[0] === '/') { - // path-absolute (hier and relative) - if (strlen($this->path) >= 2 && $this->path[1] === '/') { - // This shouldn't ever happen! - $this->path = ''; - } else { + } elseif ($this->path !== '') { + if ($this->path[0] === '/') { + // path-absolute (hier and relative) + // http:/my/path + // /my/path + if (strlen($this->path) >= 2 && $this->path[1] === '/') { + // This could happen if both the host gets stripped + // out + // http://my/path + // //my/path + $this->path = ''; + } else { + $this->path = $segments_encoder->encode($this->path); + } + } elseif (!is_null($this->scheme)) { + // path-rootless (hier) + // http:my/path + // Short circuit evaluation means we don't need to check nz $this->path = $segments_encoder->encode($this->path); - } - } elseif (!is_null($this->scheme) && $this->path !== '') { - // path-rootless (hier) - // Short circuit evaluation means we don't need to check nz - $this->path = $segments_encoder->encode($this->path); - } elseif (is_null($this->scheme) && $this->path !== '') { - // path-noscheme (relative) - // (once again, not checking nz) - $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); - $c = strpos($this->path, '/'); - if ($c !== false) { - $this->path = - $segment_nc_encoder->encode(substr($this->path, 0, $c)) . - $segments_encoder->encode(substr($this->path, $c)); } else { - $this->path = $segment_nc_encoder->encode($this->path); + // path-noscheme (relative) + // my/path + // (once again, not checking nz) + $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); + $c = strpos($this->path, '/'); + if ($c !== false) { + $this->path = + $segment_nc_encoder->encode(substr($this->path, 0, $c)) . + $segments_encoder->encode(substr($this->path, $c)); + } else { + $this->path = $segment_nc_encoder->encode($this->path); + } } } else { // path-empty (hier and relative) @@ -138,36 +207,108 @@ class HTMLPurifier_URI if (!is_null($this->fragment)) { $this->fragment = $qf_encoder->encode($this->fragment); } - return true; - } /** * Convert URI back to string - * @return String URI appropriate for output + * @return string URI appropriate for output */ - public function toString() { + public function toString() + { // reconstruct authority $authority = null; + // there is a rendering difference between a null authority + // (http:foo-bar) and an empty string authority + // (http:///foo-bar). if (!is_null($this->host)) { $authority = ''; - if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@'; + if (!is_null($this->userinfo)) { + $authority .= $this->userinfo . '@'; + } $authority .= $this->host; - if(!is_null($this->port)) $authority .= ':' . $this->port; + if (!is_null($this->port)) { + $authority .= ':' . $this->port; + } } - // reconstruct the result + // Reconstruct the result + // One might wonder about parsing quirks from browsers after + // this reconstruction. Unfortunately, parsing behavior depends + // on what *scheme* was employed (file:///foo is handled *very* + // differently than http:///foo), so unfortunately we have to + // defer to the schemes to do the right thing. $result = ''; - if (!is_null($this->scheme)) $result .= $this->scheme . ':'; - if (!is_null($authority)) $result .= '//' . $authority; + if (!is_null($this->scheme)) { + $result .= $this->scheme . ':'; + } + if (!is_null($authority)) { + $result .= '//' . $authority; + } $result .= $this->path; - if (!is_null($this->query)) $result .= '?' . $this->query; - if (!is_null($this->fragment)) $result .= '#' . $this->fragment; + if (!is_null($this->query)) { + $result .= '?' . $this->query; + } + if (!is_null($this->fragment)) { + $result .= '#' . $this->fragment; + } return $result; } + /** + * Returns true if this URL might be considered a 'local' URL given + * the current context. This is true when the host is null, or + * when it matches the host supplied to the configuration. + * + * Note that this does not do any scheme checking, so it is mostly + * only appropriate for metadata that doesn't care about protocol + * security. isBenign is probably what you actually want. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function isLocal($config, $context) + { + if ($this->host === null) { + return true; + } + $uri_def = $config->getDefinition('URI'); + if ($uri_def->host === $this->host) { + return true; + } + return false; + } + + /** + * Returns true if this URL should be considered a 'benign' URL, + * that is: + * + * - It is a local URL (isLocal), and + * - It has a equal or better level of security + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function isBenign($config, $context) + { + if (!$this->isLocal($config, $context)) { + return false; + } + + $scheme_obj = $this->getSchemeObj($config, $context); + if (!$scheme_obj) { + return false; + } // conservative approach + + $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context); + if ($current_scheme_obj->secure) { + if (!$scheme_obj->secure) { + return false; + } + } + return true; + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIDefinition.php b/library/HTMLPurifier/URIDefinition.php index ea2b8fe24..e0bd8bcca 100644 --- a/library/HTMLPurifier/URIDefinition.php +++ b/library/HTMLPurifier/URIDefinition.php @@ -23,19 +23,24 @@ class HTMLPurifier_URIDefinition extends HTMLPurifier_Definition */ public $defaultScheme; - public function __construct() { + public function __construct() + { $this->registerFilter(new HTMLPurifier_URIFilter_DisableExternal()); $this->registerFilter(new HTMLPurifier_URIFilter_DisableExternalResources()); + $this->registerFilter(new HTMLPurifier_URIFilter_DisableResources()); $this->registerFilter(new HTMLPurifier_URIFilter_HostBlacklist()); + $this->registerFilter(new HTMLPurifier_URIFilter_SafeIframe()); $this->registerFilter(new HTMLPurifier_URIFilter_MakeAbsolute()); $this->registerFilter(new HTMLPurifier_URIFilter_Munge()); } - public function registerFilter($filter) { + public function registerFilter($filter) + { $this->registeredFilters[$filter->name] = $filter; } - public function addFilter($filter, $config) { + public function addFilter($filter, $config) + { $r = $filter->prepare($config); if ($r === false) return; // null is ok, for backwards compat if ($filter->post) { @@ -45,22 +50,29 @@ class HTMLPurifier_URIDefinition extends HTMLPurifier_Definition } } - protected function doSetup($config) { + protected function doSetup($config) + { $this->setupMemberVariables($config); $this->setupFilters($config); } - protected function setupFilters($config) { + protected function setupFilters($config) + { foreach ($this->registeredFilters as $name => $filter) { - $conf = $config->get('URI.' . $name); - if ($conf !== false && $conf !== null) { + if ($filter->always_load) { $this->addFilter($filter, $config); + } else { + $conf = $config->get('URI.' . $name); + if ($conf !== false && $conf !== null) { + $this->addFilter($filter, $config); + } } } unset($this->registeredFilters); } - protected function setupMemberVariables($config) { + protected function setupMemberVariables($config) + { $this->host = $config->get('URI.Host'); $base_uri = $config->get('URI.Base'); if (!is_null($base_uri)) { @@ -72,7 +84,13 @@ class HTMLPurifier_URIDefinition extends HTMLPurifier_Definition if (is_null($this->defaultScheme)) $this->defaultScheme = $config->get('URI.DefaultScheme'); } - public function filter(&$uri, $config, $context) { + public function getDefaultScheme($config, $context) + { + return HTMLPurifier_URISchemeRegistry::instance()->getScheme($this->defaultScheme, $config, $context); + } + + public function filter(&$uri, $config, $context) + { foreach ($this->filters as $name => $f) { $result = $f->filter($uri, $config, $context); if (!$result) return false; @@ -80,7 +98,8 @@ class HTMLPurifier_URIDefinition extends HTMLPurifier_Definition return true; } - public function postFilter(&$uri, $config, $context) { + public function postFilter(&$uri, $config, $context) + { foreach ($this->postFilters as $name => $f) { $result = $f->filter($uri, $config, $context); if (!$result) return false; diff --git a/library/HTMLPurifier/URIFilter.php b/library/HTMLPurifier/URIFilter.php index c116f93df..09724e9f4 100644 --- a/library/HTMLPurifier/URIFilter.php +++ b/library/HTMLPurifier/URIFilter.php @@ -4,7 +4,21 @@ * Chainable filters for custom URI processing. * * These filters can perform custom actions on a URI filter object, - * including transformation or blacklisting. + * including transformation or blacklisting. A filter named Foo + * must have a corresponding configuration directive %URI.Foo, + * unless always_load is specified to be true. + * + * The following contexts may be available while URIFilters are being + * processed: + * + * - EmbeddedURI: true if URI is an embedded resource that will + * be loaded automatically on page load + * - CurrentToken: a reference to the token that is currently + * being processed + * - CurrentAttr: the name of the attribute that is currently being + * processed + * - CurrentCSSProperty: the name of the CSS property that is + * currently being processed (if applicable) * * @warning This filter is called before scheme object validation occurs. * Make sure, if you require a specific scheme object, you @@ -15,31 +29,46 @@ abstract class HTMLPurifier_URIFilter { /** - * Unique identifier of filter + * Unique identifier of filter. + * @type string */ public $name; /** * True if this filter should be run after scheme validation. + * @type bool */ public $post = false; /** - * Performs initialization for the filter + * True if this filter should always be loaded. + * This permits a filter to be named Foo without the corresponding + * %URI.Foo directive existing. + * @type bool + */ + public $always_load = false; + + /** + * Performs initialization for the filter. If the filter returns + * false, this means that it shouldn't be considered active. + * @param HTMLPurifier_Config $config + * @return bool */ - public function prepare($config) {return true;} + public function prepare($config) + { + return true; + } /** * Filter a URI object - * @param $uri Reference to URI object variable - * @param $config Instance of HTMLPurifier_Config - * @param $context Instance of HTMLPurifier_Context + * @param HTMLPurifier_URI $uri Reference to URI object variable + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context * @return bool Whether or not to continue processing: false indicates * URL is no good, true indicates continue processing. Note that * all changes are committed directly on the URI object */ abstract public function filter(&$uri, $config, $context); - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIFilter/DisableExternal.php b/library/HTMLPurifier/URIFilter/DisableExternal.php index d8a39a501..ced1b1376 100644 --- a/library/HTMLPurifier/URIFilter/DisableExternal.php +++ b/library/HTMLPurifier/URIFilter/DisableExternal.php @@ -2,19 +2,50 @@ class HTMLPurifier_URIFilter_DisableExternal extends HTMLPurifier_URIFilter { + /** + * @type string + */ public $name = 'DisableExternal'; + + /** + * @type array + */ protected $ourHostParts = false; - public function prepare($config) { + + /** + * @param HTMLPurifier_Config $config + * @return void + */ + public function prepare($config) + { $our_host = $config->getDefinition('URI')->host; - if ($our_host !== null) $this->ourHostParts = array_reverse(explode('.', $our_host)); + if ($our_host !== null) { + $this->ourHostParts = array_reverse(explode('.', $our_host)); + } } - public function filter(&$uri, $config, $context) { - if (is_null($uri->host)) return true; - if ($this->ourHostParts === false) return false; + + /** + * @param HTMLPurifier_URI $uri Reference + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if (is_null($uri->host)) { + return true; + } + if ($this->ourHostParts === false) { + return false; + } $host_parts = array_reverse(explode('.', $uri->host)); foreach ($this->ourHostParts as $i => $x) { - if (!isset($host_parts[$i])) return false; - if ($host_parts[$i] != $this->ourHostParts[$i]) return false; + if (!isset($host_parts[$i])) { + return false; + } + if ($host_parts[$i] != $this->ourHostParts[$i]) { + return false; + } } return true; } diff --git a/library/HTMLPurifier/URIFilter/DisableExternalResources.php b/library/HTMLPurifier/URIFilter/DisableExternalResources.php index 881abc43c..c6562169e 100644 --- a/library/HTMLPurifier/URIFilter/DisableExternalResources.php +++ b/library/HTMLPurifier/URIFilter/DisableExternalResources.php @@ -2,9 +2,22 @@ class HTMLPurifier_URIFilter_DisableExternalResources extends HTMLPurifier_URIFilter_DisableExternal { + /** + * @type string + */ public $name = 'DisableExternalResources'; - public function filter(&$uri, $config, $context) { - if (!$context->get('EmbeddedURI', true)) return true; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if (!$context->get('EmbeddedURI', true)) { + return true; + } return parent::filter($uri, $config, $context); } } diff --git a/library/HTMLPurifier/URIFilter/DisableResources.php b/library/HTMLPurifier/URIFilter/DisableResources.php new file mode 100644 index 000000000..d5c412c44 --- /dev/null +++ b/library/HTMLPurifier/URIFilter/DisableResources.php @@ -0,0 +1,22 @@ +<?php + +class HTMLPurifier_URIFilter_DisableResources extends HTMLPurifier_URIFilter +{ + /** + * @type string + */ + public $name = 'DisableResources'; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + return !$context->get('EmbeddedURI', true); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIFilter/HostBlacklist.php b/library/HTMLPurifier/URIFilter/HostBlacklist.php index 045aa0992..a6645c17e 100644 --- a/library/HTMLPurifier/URIFilter/HostBlacklist.php +++ b/library/HTMLPurifier/URIFilter/HostBlacklist.php @@ -1,15 +1,40 @@ <?php +// It's not clear to me whether or not Punycode means that hostnames +// do not have canonical forms anymore. As far as I can tell, it's +// not a problem (punycoding should be identity when no Unicode +// points are involved), but I'm not 100% sure class HTMLPurifier_URIFilter_HostBlacklist extends HTMLPurifier_URIFilter { + /** + * @type string + */ public $name = 'HostBlacklist'; + + /** + * @type array + */ protected $blacklist = array(); - public function prepare($config) { + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function prepare($config) + { $this->blacklist = $config->get('URI.HostBlacklist'); return true; } - public function filter(&$uri, $config, $context) { - foreach($this->blacklist as $blacklisted_host_fragment) { + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + foreach ($this->blacklist as $blacklisted_host_fragment) { if (strpos($uri->host, $blacklisted_host_fragment) !== false) { return false; } diff --git a/library/HTMLPurifier/URIFilter/MakeAbsolute.php b/library/HTMLPurifier/URIFilter/MakeAbsolute.php index f46ab2630..c507bbff8 100644 --- a/library/HTMLPurifier/URIFilter/MakeAbsolute.php +++ b/library/HTMLPurifier/URIFilter/MakeAbsolute.php @@ -4,14 +4,35 @@ class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter { + /** + * @type string + */ public $name = 'MakeAbsolute'; + + /** + * @type + */ protected $base; + + /** + * @type array + */ protected $basePathStack = array(); - public function prepare($config) { + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function prepare($config) + { $def = $config->getDefinition('URI'); $this->base = $def->base; if (is_null($this->base)) { - trigger_error('URI.MakeAbsolute is being ignored due to lack of value for URI.Base configuration', E_USER_WARNING); + trigger_error( + 'URI.MakeAbsolute is being ignored due to lack of ' . + 'value for URI.Base configuration', + E_USER_WARNING + ); return false; } $this->base->fragment = null; // fragment is invalid for base URI @@ -21,19 +42,29 @@ class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter $this->basePathStack = $stack; return true; } - public function filter(&$uri, $config, $context) { - if (is_null($this->base)) return true; // abort early - if ( - $uri->path === '' && is_null($uri->scheme) && - is_null($uri->host) && is_null($uri->query) && is_null($uri->fragment) - ) { + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if (is_null($this->base)) { + return true; + } // abort early + if ($uri->path === '' && is_null($uri->scheme) && + is_null($uri->host) && is_null($uri->query) && is_null($uri->fragment)) { // reference to current document $uri = clone $this->base; return true; } if (!is_null($uri->scheme)) { // absolute URI already: don't change - if (!is_null($uri->host)) return true; + if (!is_null($uri->host)) { + return true; + } $scheme_obj = $uri->getSchemeObj($config, $context); if (!$scheme_obj) { // scheme not recognized @@ -66,22 +97,33 @@ class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter } // re-combine $uri->scheme = $this->base->scheme; - if (is_null($uri->userinfo)) $uri->userinfo = $this->base->userinfo; - if (is_null($uri->host)) $uri->host = $this->base->host; - if (is_null($uri->port)) $uri->port = $this->base->port; + if (is_null($uri->userinfo)) { + $uri->userinfo = $this->base->userinfo; + } + if (is_null($uri->host)) { + $uri->host = $this->base->host; + } + if (is_null($uri->port)) { + $uri->port = $this->base->port; + } return true; } /** * Resolve dots and double-dots in a path stack + * @param array $stack + * @return array */ - private function _collapseStack($stack) { + private function _collapseStack($stack) + { $result = array(); $is_folder = false; for ($i = 0; isset($stack[$i]); $i++) { $is_folder = false; // absorb an internally duplicated slash - if ($stack[$i] == '' && $i && isset($stack[$i+1])) continue; + if ($stack[$i] == '' && $i && isset($stack[$i + 1])) { + continue; + } if ($stack[$i] == '..') { if (!empty($result)) { $segment = array_pop($result); @@ -106,7 +148,9 @@ class HTMLPurifier_URIFilter_MakeAbsolute extends HTMLPurifier_URIFilter } $result[] = $stack[$i]; } - if ($is_folder) $result[] = ''; + if ($is_folder) { + $result[] = ''; + } return $result; } } diff --git a/library/HTMLPurifier/URIFilter/Munge.php b/library/HTMLPurifier/URIFilter/Munge.php index efa10a645..6e03315a1 100644 --- a/library/HTMLPurifier/URIFilter/Munge.php +++ b/library/HTMLPurifier/URIFilter/Munge.php @@ -2,31 +2,79 @@ class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter { + /** + * @type string + */ public $name = 'Munge'; + + /** + * @type bool + */ public $post = true; - private $target, $parser, $doEmbed, $secretKey; + /** + * @type string + */ + private $target; + + /** + * @type HTMLPurifier_URIParser + */ + private $parser; + + /** + * @type bool + */ + private $doEmbed; + + /** + * @type string + */ + private $secretKey; + + /** + * @type array + */ protected $replace = array(); - public function prepare($config) { - $this->target = $config->get('URI.' . $this->name); - $this->parser = new HTMLPurifier_URIParser(); - $this->doEmbed = $config->get('URI.MungeResources'); + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function prepare($config) + { + $this->target = $config->get('URI.' . $this->name); + $this->parser = new HTMLPurifier_URIParser(); + $this->doEmbed = $config->get('URI.MungeResources'); $this->secretKey = $config->get('URI.MungeSecretKey'); + if ($this->secretKey && !function_exists('hash_hmac')) { + throw new Exception("Cannot use %URI.MungeSecretKey without hash_hmac support."); + } return true; } - public function filter(&$uri, $config, $context) { - if ($context->get('EmbeddedURI', true) && !$this->doEmbed) return true; - $scheme_obj = $uri->getSchemeObj($config, $context); - if (!$scheme_obj) return true; // ignore unknown schemes, maybe another postfilter did it - if (is_null($uri->host) || empty($scheme_obj->browsable)) { + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if ($context->get('EmbeddedURI', true) && !$this->doEmbed) { return true; } - // don't redirect if target host is our host - if ($uri->host === $config->getDefinition('URI')->host) { + + $scheme_obj = $uri->getSchemeObj($config, $context); + if (!$scheme_obj) { return true; - } + } // ignore unknown schemes, maybe another postfilter did it + if (!$scheme_obj->browsable) { + return true; + } // ignore non-browseable schemes, since we can't munge those in a reasonable way + if ($uri->isBenign($config, $context)) { + return true; + } // don't redirect if a benign URL $this->makeReplace($uri, $config, $context); $this->replace = array_map('rawurlencode', $this->replace); @@ -35,12 +83,20 @@ class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter $new_uri = $this->parser->parse($new_uri); // don't redirect if the target host is the same as the // starting host - if ($uri->host === $new_uri->host) return true; + if ($uri->host === $new_uri->host) { + return true; + } $uri = $new_uri; // overwrite return true; } - protected function makeReplace($uri, $config, $context) { + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + protected function makeReplace($uri, $config, $context) + { $string = $uri->toString(); // always available $this->replace['%s'] = $string; @@ -50,9 +106,10 @@ class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter $this->replace['%m'] = $context->get('CurrentAttr', true); $this->replace['%p'] = $context->get('CurrentCSSProperty', true); // not always available - if ($this->secretKey) $this->replace['%t'] = sha1($this->secretKey . ':' . $string); + if ($this->secretKey) { + $this->replace['%t'] = hash_hmac("sha256", $string, $this->secretKey); + } } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIFilter/SafeIframe.php b/library/HTMLPurifier/URIFilter/SafeIframe.php new file mode 100644 index 000000000..f609c47a3 --- /dev/null +++ b/library/HTMLPurifier/URIFilter/SafeIframe.php @@ -0,0 +1,68 @@ +<?php + +/** + * Implements safety checks for safe iframes. + * + * @warning This filter is *critical* for ensuring that %HTML.SafeIframe + * works safely. + */ +class HTMLPurifier_URIFilter_SafeIframe extends HTMLPurifier_URIFilter +{ + /** + * @type string + */ + public $name = 'SafeIframe'; + + /** + * @type bool + */ + public $always_load = true; + + /** + * @type string + */ + protected $regexp = null; + + // XXX: The not so good bit about how this is all set up now is we + // can't check HTML.SafeIframe in the 'prepare' step: we have to + // defer till the actual filtering. + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function prepare($config) + { + $this->regexp = $config->get('URI.SafeIframeRegexp'); + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + // check if filter not applicable + if (!$config->get('HTML.SafeIframe')) { + return true; + } + // check if the filter should actually trigger + if (!$context->get('EmbeddedURI', true)) { + return true; + } + $token = $context->get('CurrentToken', true); + if (!($token && $token->name == 'iframe')) { + return true; + } + // check if we actually have some whitelists enabled + if ($this->regexp === null) { + return false; + } + // actually check the whitelists + return preg_match($this->regexp, $uri->toString()); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIParser.php b/library/HTMLPurifier/URIParser.php index 7179e4ab8..0e7381a07 100644 --- a/library/HTMLPurifier/URIParser.php +++ b/library/HTMLPurifier/URIParser.php @@ -12,7 +12,8 @@ class HTMLPurifier_URIParser */ protected $percentEncoder; - public function __construct() { + public function __construct() + { $this->percentEncoder = new HTMLPurifier_PercentEncoder(); } @@ -22,15 +23,15 @@ class HTMLPurifier_URIParser * @return HTMLPurifier_URI representation of URI. This representation has * not been validated yet and may not conform to RFC. */ - public function parse($uri) { - + public function parse($uri) + { $uri = $this->percentEncoder->normalize($uri); // Regexp is as per Appendix B. // Note that ["<>] are an addition to the RFC's recommended // characters, because they represent external delimeters. $r_URI = '!'. - '(([^:/?#"<>]+):)?'. // 2. Scheme + '(([a-zA-Z0-9\.\+\-]+):)?'. // 2. Scheme '(//([^/?#"<>]*))?'. // 4. Authority '([^?#"<>]*)'. // 5. Path '(\?([^#"<>]*))?'. // 7. Query diff --git a/library/HTMLPurifier/URIScheme.php b/library/HTMLPurifier/URIScheme.php index 039710fd1..fe9e82cf2 100644 --- a/library/HTMLPurifier/URIScheme.php +++ b/library/HTMLPurifier/URIScheme.php @@ -3,40 +3,100 @@ /** * Validator for the components of a URI for a specific scheme */ -class HTMLPurifier_URIScheme +abstract class HTMLPurifier_URIScheme { /** - * Scheme's default port (integer) + * Scheme's default port (integer). If an explicit port number is + * specified that coincides with the default port, it will be + * elided. + * @type int */ public $default_port = null; /** - * Whether or not URIs of this schem are locatable by a browser + * Whether or not URIs of this scheme are locatable by a browser * http and ftp are accessible, while mailto and news are not. + * @type bool */ public $browsable = false; /** + * Whether or not data transmitted over this scheme is encrypted. + * https is secure, http is not. + * @type bool + */ + public $secure = false; + + /** * Whether or not the URI always uses <hier_part>, resolves edge cases * with making relative URIs absolute + * @type bool */ public $hierarchical = false; /** - * Validates the components of a URI - * @note This implementation should be called by children if they define - * a default port, as it does port processing. - * @param $uri Instance of HTMLPurifier_URI - * @param $config HTMLPurifier_Config object - * @param $context HTMLPurifier_Context object - * @return Bool success or failure + * Whether or not the URI may omit a hostname when the scheme is + * explicitly specified, ala file:///path/to/file. As of writing, + * 'file' is the only scheme that browsers support his properly. + * @type bool */ - public function validate(&$uri, $config, $context) { - if ($this->default_port == $uri->port) $uri->port = null; - return true; - } + public $may_omit_host = false; + + /** + * Validates the components of a URI for a specific scheme. + * @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool success or failure + */ + abstract public function doValidate(&$uri, $config, $context); + /** + * Public interface for validating components of a URI. Performs a + * bunch of default actions. Don't overload this method. + * @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool success or failure + */ + public function validate(&$uri, $config, $context) + { + if ($this->default_port == $uri->port) { + $uri->port = null; + } + // kludge: browsers do funny things when the scheme but not the + // authority is set + if (!$this->may_omit_host && + // if the scheme is present, a missing host is always in error + (!is_null($uri->scheme) && ($uri->host === '' || is_null($uri->host))) || + // if the scheme is not present, a *blank* host is in error, + // since this translates into '///path' which most browsers + // interpret as being 'http://path'. + (is_null($uri->scheme) && $uri->host === '') + ) { + do { + if (is_null($uri->scheme)) { + if (substr($uri->path, 0, 2) != '//') { + $uri->host = null; + break; + } + // URI is '////path', so we cannot nullify the + // host to preserve semantics. Try expanding the + // hostname instead (fall through) + } + // first see if we can manually insert a hostname + $host = $config->get('URI.Host'); + if (!is_null($host)) { + $uri->host = $host; + } else { + // we can't do anything sensible, reject the URL. + return false; + } + } while (false); + } + return $this->doValidate($uri, $config, $context); + } } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/data.php b/library/HTMLPurifier/URIScheme/data.php index b7f1989cb..6ebca4984 100644 --- a/library/HTMLPurifier/URIScheme/data.php +++ b/library/HTMLPurifier/URIScheme/data.php @@ -3,18 +3,38 @@ /** * Implements data: URI for base64 encoded images supported by GD. */ -class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme { - +class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme +{ + /** + * @type bool + */ public $browsable = true; + + /** + * @type array + */ public $allowed_types = array( // you better write validation code for other types if you // decide to allow them 'image/jpeg' => true, 'image/gif' => true, 'image/png' => true, - ); + ); + // this is actually irrelevant since we only write out the path + // component + /** + * @type bool + */ + public $may_omit_host = true; - public function validate(&$uri, $config, $context) { + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { $result = explode(',', $uri->path, 2); $is_base64 = false; $charset = null; @@ -23,7 +43,7 @@ class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme { list($metadata, $data) = $result; // do some legwork on the metadata $metas = explode(';', $metadata); - while(!empty($metas)) { + while (!empty($metas)) { $cur = array_shift($metas); if ($cur == 'base64') { $is_base64 = true; @@ -32,10 +52,14 @@ class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme { if (substr($cur, 0, 8) == 'charset=') { // doesn't match if there are arbitrary spaces, but // whatever dude - if ($charset !== null) continue; // garbage + if ($charset !== null) { + continue; + } // garbage $charset = substr($cur, 8); // not used } else { - if ($content_type !== null) continue; // garbage + if ($content_type !== null) { + continue; + } // garbage $content_type = $cur; } } @@ -61,11 +85,15 @@ class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme { file_put_contents($file, $raw_data); if (function_exists('exif_imagetype')) { $image_code = exif_imagetype($file); + unlink($file); } elseif (function_exists('getimagesize')) { set_error_handler(array($this, 'muteErrorHandler')); $info = getimagesize($file); restore_error_handler(); - if ($info == false) return false; + unlink($file); + if ($info == false) { + return false; + } $image_code = $info[2]; } else { trigger_error("could not find exif_imagetype or getimagesize functions", E_USER_ERROR); @@ -74,7 +102,9 @@ class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme { if ($real_content_type != $content_type) { // we're nice guys; if the content type is something else we // support, change it over - if (empty($this->allowed_types[$real_content_type])) return false; + if (empty($this->allowed_types[$real_content_type])) { + return false; + } $content_type = $real_content_type; } // ok, it's kosher, rewrite what we need @@ -87,7 +117,11 @@ class HTMLPurifier_URIScheme_data extends HTMLPurifier_URIScheme { return true; } - public function muteErrorHandler($errno, $errstr) {} - + /** + * @param int $errno + * @param string $errstr + */ + public function muteErrorHandler($errno, $errstr) + { + } } - diff --git a/library/HTMLPurifier/URIScheme/file.php b/library/HTMLPurifier/URIScheme/file.php new file mode 100644 index 000000000..215be4ba8 --- /dev/null +++ b/library/HTMLPurifier/URIScheme/file.php @@ -0,0 +1,44 @@ +<?php + +/** + * Validates file as defined by RFC 1630 and RFC 1738. + */ +class HTMLPurifier_URIScheme_file extends HTMLPurifier_URIScheme +{ + /** + * Generally file:// URLs are not accessible from most + * machines, so placing them as an img src is incorrect. + * @type bool + */ + public $browsable = false; + + /** + * Basically the *only* URI scheme for which this is true, since + * accessing files on the local machine is very common. In fact, + * browsers on some operating systems don't understand the + * authority, though I hear it is used on Windows to refer to + * network shares. + * @type bool + */ + public $may_omit_host = true; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { + // Authentication method is not supported + $uri->userinfo = null; + // file:// makes no provisions for accessing the resource + $uri->port = null; + // While it seems to work on Firefox, the querystring has + // no possible effect and is thus stripped. + $uri->query = null; + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/ftp.php b/library/HTMLPurifier/URIScheme/ftp.php index 5849bf7ff..1eb43ee5c 100644 --- a/library/HTMLPurifier/URIScheme/ftp.php +++ b/library/HTMLPurifier/URIScheme/ftp.php @@ -3,15 +3,32 @@ /** * Validates ftp (File Transfer Protocol) URIs as defined by generic RFC 1738. */ -class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme { - +class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme +{ + /** + * @type int + */ public $default_port = 21; + + /** + * @type bool + */ public $browsable = true; // usually + + /** + * @type bool + */ public $hierarchical = true; - public function validate(&$uri, $config, $context) { - parent::validate($uri, $config, $context); - $uri->query = null; + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { + $uri->query = null; // typecode check $semicolon_pos = strrpos($uri->path, ';'); // reverse @@ -34,10 +51,8 @@ class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme { $uri->path = str_replace(';', '%3B', $uri->path); $uri->path .= $type_ret; } - return true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/http.php b/library/HTMLPurifier/URIScheme/http.php index b097a31d6..ce69ec438 100644 --- a/library/HTMLPurifier/URIScheme/http.php +++ b/library/HTMLPurifier/URIScheme/http.php @@ -3,18 +3,34 @@ /** * Validates http (HyperText Transfer Protocol) as defined by RFC 2616 */ -class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme { - +class HTMLPurifier_URIScheme_http extends HTMLPurifier_URIScheme +{ + /** + * @type int + */ public $default_port = 80; + + /** + * @type bool + */ public $browsable = true; + + /** + * @type bool + */ public $hierarchical = true; - public function validate(&$uri, $config, $context) { - parent::validate($uri, $config, $context); + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { $uri->userinfo = null; return true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/https.php b/library/HTMLPurifier/URIScheme/https.php index 29e380919..0e96882db 100644 --- a/library/HTMLPurifier/URIScheme/https.php +++ b/library/HTMLPurifier/URIScheme/https.php @@ -3,10 +3,16 @@ /** * Validates https (Secure HTTP) according to http scheme. */ -class HTMLPurifier_URIScheme_https extends HTMLPurifier_URIScheme_http { - +class HTMLPurifier_URIScheme_https extends HTMLPurifier_URIScheme_http +{ + /** + * @type int + */ public $default_port = 443; - + /** + * @type bool + */ + public $secure = true; } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/mailto.php b/library/HTMLPurifier/URIScheme/mailto.php index c1e2cd5aa..c3a6b602a 100644 --- a/library/HTMLPurifier/URIScheme/mailto.php +++ b/library/HTMLPurifier/URIScheme/mailto.php @@ -9,19 +9,32 @@ * @todo Filter allowed query parameters */ -class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme { - +class HTMLPurifier_URIScheme_mailto extends HTMLPurifier_URIScheme +{ + /** + * @type bool + */ public $browsable = false; - public function validate(&$uri, $config, $context) { - parent::validate($uri, $config, $context); + /** + * @type bool + */ + public $may_omit_host = true; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { $uri->userinfo = null; $uri->host = null; $uri->port = null; // we need to validate path against RFC 2368's addr-spec return true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/news.php b/library/HTMLPurifier/URIScheme/news.php index f5f54f4f5..7490927d6 100644 --- a/library/HTMLPurifier/URIScheme/news.php +++ b/library/HTMLPurifier/URIScheme/news.php @@ -3,20 +3,33 @@ /** * Validates news (Usenet) as defined by generic RFC 1738 */ -class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme { - +class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme +{ + /** + * @type bool + */ public $browsable = false; - public function validate(&$uri, $config, $context) { - parent::validate($uri, $config, $context); + /** + * @type bool + */ + public $may_omit_host = true; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { $uri->userinfo = null; - $uri->host = null; - $uri->port = null; - $uri->query = null; + $uri->host = null; + $uri->port = null; + $uri->query = null; // typecode check needed on path return true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URIScheme/nntp.php b/library/HTMLPurifier/URIScheme/nntp.php index 5bf93ea78..f211d715e 100644 --- a/library/HTMLPurifier/URIScheme/nntp.php +++ b/library/HTMLPurifier/URIScheme/nntp.php @@ -3,18 +3,30 @@ /** * Validates nntp (Network News Transfer Protocol) as defined by generic RFC 1738 */ -class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme { - +class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme +{ + /** + * @type int + */ public $default_port = 119; + + /** + * @type bool + */ public $browsable = false; - public function validate(&$uri, $config, $context) { - parent::validate($uri, $config, $context); + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { $uri->userinfo = null; - $uri->query = null; + $uri->query = null; return true; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/URISchemeRegistry.php b/library/HTMLPurifier/URISchemeRegistry.php index 576bf7b6d..4ac8a0b76 100644 --- a/library/HTMLPurifier/URISchemeRegistry.php +++ b/library/HTMLPurifier/URISchemeRegistry.php @@ -8,12 +8,14 @@ class HTMLPurifier_URISchemeRegistry /** * Retrieve sole instance of the registry. - * @param $prototype Optional prototype to overload sole instance with, + * @param HTMLPurifier_URISchemeRegistry $prototype Optional prototype to overload sole instance with, * or bool true to reset to default registry. + * @return HTMLPurifier_URISchemeRegistry * @note Pass a registry object $prototype with a compatible interface and * the function will copy it and return it all further times. */ - public static function instance($prototype = null) { + public static function instance($prototype = null) + { static $instance = null; if ($prototype !== null) { $instance = $prototype; @@ -25,17 +27,22 @@ class HTMLPurifier_URISchemeRegistry /** * Cache of retrieved schemes. + * @type HTMLPurifier_URIScheme[] */ protected $schemes = array(); /** * Retrieves a scheme validator object - * @param $scheme String scheme name like http or mailto - * @param $config HTMLPurifier_Config object - * @param $config HTMLPurifier_Context object + * @param string $scheme String scheme name like http or mailto + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_URIScheme */ - public function getScheme($scheme, $config, $context) { - if (!$config) $config = HTMLPurifier_Config::createDefault(); + public function getScheme($scheme, $config, $context) + { + if (!$config) { + $config = HTMLPurifier_Config::createDefault(); + } // important, otherwise attacker could include arbitrary file $allowed_schemes = $config->get('URI.AllowedSchemes'); @@ -45,24 +52,30 @@ class HTMLPurifier_URISchemeRegistry return; } - if (isset($this->schemes[$scheme])) return $this->schemes[$scheme]; - if (!isset($allowed_schemes[$scheme])) return; + if (isset($this->schemes[$scheme])) { + return $this->schemes[$scheme]; + } + if (!isset($allowed_schemes[$scheme])) { + return; + } $class = 'HTMLPurifier_URIScheme_' . $scheme; - if (!class_exists($class)) return; + if (!class_exists($class)) { + return; + } $this->schemes[$scheme] = new $class(); return $this->schemes[$scheme]; } /** * Registers a custom scheme to the cache, bypassing reflection. - * @param $scheme Scheme name - * @param $scheme_obj HTMLPurifier_URIScheme object + * @param string $scheme Scheme name + * @param HTMLPurifier_URIScheme $scheme_obj */ - public function register($scheme, $scheme_obj) { + public function register($scheme, $scheme_obj) + { $this->schemes[$scheme] = $scheme_obj; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/UnitConverter.php b/library/HTMLPurifier/UnitConverter.php index 545d42622..166f3bf30 100644 --- a/library/HTMLPurifier/UnitConverter.php +++ b/library/HTMLPurifier/UnitConverter.php @@ -37,20 +37,24 @@ class HTMLPurifier_UnitConverter /** * Minimum bcmath precision for output. + * @type int */ protected $outputPrecision; /** * Bcmath precision for internal calculations. + * @type int */ protected $internalPrecision; /** - * Whether or not BCMath is available + * Whether or not BCMath is available. + * @type bool */ private $bcmath; - public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) { + public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) + { $this->outputPrecision = $output_precision; $this->internalPrecision = $internal_precision; $this->bcmath = !$force_no_bcmath && function_exists('bcmul'); @@ -63,6 +67,7 @@ class HTMLPurifier_UnitConverter * it before passing it here! * @param string $to_unit * Unit to convert to. + * @return HTMLPurifier_Length|bool * @note * About precision: This conversion function pays very special * attention to the incoming precision of values and attempts @@ -74,11 +79,13 @@ class HTMLPurifier_UnitConverter * and this causes some decimals to be excluded, those * decimals will be added on. */ - public function convert($length, $to_unit) { - - if (!$length->isValid()) return false; + public function convert($length, $to_unit) + { + if (!$length->isValid()) { + return false; + } - $n = $length->getN(); + $n = $length->getN(); $unit = $length->getUnit(); if ($n === '0' || $unit === false) { @@ -87,21 +94,29 @@ class HTMLPurifier_UnitConverter $state = $dest_state = false; foreach (self::$units as $k => $x) { - if (isset($x[$unit])) $state = $k; - if (isset($x[$to_unit])) $dest_state = $k; + if (isset($x[$unit])) { + $state = $k; + } + if (isset($x[$to_unit])) { + $dest_state = $k; + } + } + if (!$state || !$dest_state) { + return false; } - if (!$state || !$dest_state) return false; // Some calculations about the initial precision of the number; // this will be useful when we need to do final rounding. $sigfigs = $this->getSigFigs($n); - if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision; + if ($sigfigs < $this->outputPrecision) { + $sigfigs = $this->outputPrecision; + } // BCMath's internal precision deals only with decimals. Use // our default if the initial number has no decimals, or increase // it by how ever many decimals, thus, the number of guard digits // will always be greater than or equal to internalPrecision. - $log = (int) floor(log(abs($n), 10)); + $log = (int)floor(log(abs($n), 10)); $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision for ($i = 0; $i < 2; $i++) { @@ -152,14 +167,18 @@ class HTMLPurifier_UnitConverter } // Post-condition: $unit == $to_unit - if ($unit !== $to_unit) return false; + if ($unit !== $to_unit) { + return false; + } // Useful for debugging: //echo "<pre>n"; //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n"; $n = $this->round($n, $sigfigs); - if (strpos($n, '.') !== false) $n = rtrim($n, '0'); + if (strpos($n, '.') !== false) { + $n = rtrim($n, '0'); + } $n = rtrim($n, '.'); return new HTMLPurifier_Length($n, $unit); @@ -170,53 +189,84 @@ class HTMLPurifier_UnitConverter * @param string $n Decimal number * @return int number of sigfigs */ - public function getSigFigs($n) { + public function getSigFigs($n) + { $n = ltrim($n, '0+-'); $dp = strpos($n, '.'); // decimal position if ($dp === false) { $sigfigs = strlen(rtrim($n, '0')); } else { $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character - if ($dp !== 0) $sigfigs--; + if ($dp !== 0) { + $sigfigs--; + } } return $sigfigs; } /** * Adds two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string */ - private function add($s1, $s2, $scale) { - if ($this->bcmath) return bcadd($s1, $s2, $scale); - else return $this->scale($s1 + $s2, $scale); + private function add($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcadd($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 + (float)$s2, $scale); + } } /** * Multiples two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string */ - private function mul($s1, $s2, $scale) { - if ($this->bcmath) return bcmul($s1, $s2, $scale); - else return $this->scale($s1 * $s2, $scale); + private function mul($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcmul($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 * (float)$s2, $scale); + } } /** * Divides two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string */ - private function div($s1, $s2, $scale) { - if ($this->bcmath) return bcdiv($s1, $s2, $scale); - else return $this->scale($s1 / $s2, $scale); + private function div($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcdiv($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 / (float)$s2, $scale); + } } /** * Rounds a number according to the number of sigfigs it should have, * using arbitrary precision when available. + * @param float $n + * @param int $sigfigs + * @return string */ - private function round($n, $sigfigs) { - $new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1 + private function round($n, $sigfigs) + { + $new_log = (int)floor(log(abs($n), 10)); // Number of digits left of decimal - 1 $rp = $sigfigs - $new_log - 1; // Number of decimal places needed $neg = $n < 0 ? '-' : ''; // Negative sign if ($this->bcmath) { if ($rp >= 0) { - $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); + $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); $n = bcdiv($n, '1', $rp); } else { // This algorithm partially depends on the standardized @@ -232,23 +282,26 @@ class HTMLPurifier_UnitConverter /** * Scales a float to $scale digits right of decimal point, like BCMath. + * @param float $r + * @param int $scale + * @return string */ - private function scale($r, $scale) { + private function scale($r, $scale) + { if ($scale < 0) { // The f sprintf type doesn't support negative numbers, so we // need to cludge things manually. First get the string. - $r = sprintf('%.0f', (float) $r); + $r = sprintf('%.0f', (float)$r); // Due to floating point precision loss, $r will more than likely // look something like 4652999999999.9234. We grab one more digit // than we need to precise from $r and then use that to round // appropriately. - $precise = (string) round(substr($r, 0, strlen($r) + $scale), -1); + $precise = (string)round(substr($r, 0, strlen($r) + $scale), -1); // Now we return it, truncating the zero that was rounded off. return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); } - return sprintf('%.' . $scale . 'f', (float) $r); + return sprintf('%.' . $scale . 'f', (float)$r); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/VarParser.php b/library/HTMLPurifier/VarParser.php index 68e72ae86..50cba6910 100644 --- a/library/HTMLPurifier/VarParser.php +++ b/library/HTMLPurifier/VarParser.php @@ -7,58 +7,59 @@ class HTMLPurifier_VarParser { - const STRING = 1; - const ISTRING = 2; - const TEXT = 3; - const ITEXT = 4; - const INT = 5; - const FLOAT = 6; - const BOOL = 7; - const LOOKUP = 8; - const ALIST = 9; - const HASH = 10; - const MIXED = 11; + const STRING = 1; + const ISTRING = 2; + const TEXT = 3; + const ITEXT = 4; + const INT = 5; + const FLOAT = 6; + const BOOL = 7; + const LOOKUP = 8; + const ALIST = 9; + const HASH = 10; + const MIXED = 11; /** * Lookup table of allowed types. Mainly for backwards compatibility, but * also convenient for transforming string type names to the integer constants. */ - static public $types = array( - 'string' => self::STRING, - 'istring' => self::ISTRING, - 'text' => self::TEXT, - 'itext' => self::ITEXT, - 'int' => self::INT, - 'float' => self::FLOAT, - 'bool' => self::BOOL, - 'lookup' => self::LOOKUP, - 'list' => self::ALIST, - 'hash' => self::HASH, - 'mixed' => self::MIXED + public static $types = array( + 'string' => self::STRING, + 'istring' => self::ISTRING, + 'text' => self::TEXT, + 'itext' => self::ITEXT, + 'int' => self::INT, + 'float' => self::FLOAT, + 'bool' => self::BOOL, + 'lookup' => self::LOOKUP, + 'list' => self::ALIST, + 'hash' => self::HASH, + 'mixed' => self::MIXED ); /** * Lookup table of types that are string, and can have aliases or * allowed value lists. */ - static public $stringTypes = array( - self::STRING => true, - self::ISTRING => true, - self::TEXT => true, - self::ITEXT => true, + public static $stringTypes = array( + self::STRING => true, + self::ISTRING => true, + self::TEXT => true, + self::ITEXT => true, ); /** - * Validate a variable according to type. Throws - * HTMLPurifier_VarParserException if invalid. + * Validate a variable according to type. * It may return NULL as a valid type if $allow_null is true. * - * @param $var Variable to validate - * @param $type Type of variable, see HTMLPurifier_VarParser->types - * @param $allow_null Whether or not to permit null as a value - * @return Validated and type-coerced variable + * @param mixed $var Variable to validate + * @param int $type Type of variable, see HTMLPurifier_VarParser->types + * @param bool $allow_null Whether or not to permit null as a value + * @return string Validated and type-coerced variable + * @throws HTMLPurifier_VarParserException */ - final public function parse($var, $type, $allow_null = false) { + final public function parse($var, $type, $allow_null = false) + { if (is_string($type)) { if (!isset(HTMLPurifier_VarParser::$types[$type])) { throw new HTMLPurifier_VarParserException("Invalid type '$type'"); @@ -67,7 +68,9 @@ class HTMLPurifier_VarParser } } $var = $this->parseImplementation($var, $type, $allow_null); - if ($allow_null && $var === null) return null; + if ($allow_null && $var === null) { + return null; + } // These are basic checks, to make sure nothing horribly wrong // happened in our implementations. switch ($type) { @@ -75,27 +78,45 @@ class HTMLPurifier_VarParser case (self::ISTRING): case (self::TEXT): case (self::ITEXT): - if (!is_string($var)) break; - if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var); + if (!is_string($var)) { + break; + } + if ($type == self::ISTRING || $type == self::ITEXT) { + $var = strtolower($var); + } return $var; case (self::INT): - if (!is_int($var)) break; + if (!is_int($var)) { + break; + } return $var; case (self::FLOAT): - if (!is_float($var)) break; + if (!is_float($var)) { + break; + } return $var; case (self::BOOL): - if (!is_bool($var)) break; + if (!is_bool($var)) { + break; + } return $var; case (self::LOOKUP): case (self::ALIST): case (self::HASH): - if (!is_array($var)) break; + if (!is_array($var)) { + break; + } if ($type === self::LOOKUP) { - foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true'); + foreach ($var as $k) { + if ($k !== true) { + $this->error('Lookup table contains value other than true'); + } + } } elseif ($type === self::ALIST) { $keys = array_keys($var); - if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform'); + if (array_keys($keys) !== $keys) { + $this->error('Indices for list are not uniform'); + } } return $var; case (self::MIXED): @@ -107,17 +128,24 @@ class HTMLPurifier_VarParser } /** - * Actually implements the parsing. Base implementation is to not + * Actually implements the parsing. Base implementation does not * do anything to $var. Subclasses should overload this! + * @param mixed $var + * @param int $type + * @param bool $allow_null + * @return string */ - protected function parseImplementation($var, $type, $allow_null) { + protected function parseImplementation($var, $type, $allow_null) + { return $var; } /** * Throws an exception. + * @throws HTMLPurifier_VarParserException */ - protected function error($msg) { + protected function error($msg) + { throw new HTMLPurifier_VarParserException($msg); } @@ -126,29 +154,45 @@ class HTMLPurifier_VarParser * @note This should not ever be called. It would be called if we * extend the allowed values of HTMLPurifier_VarParser without * updating subclasses. + * @param string $class + * @param int $type + * @throws HTMLPurifier_Exception */ - protected function errorInconsistent($class, $type) { - throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented"); + protected function errorInconsistent($class, $type) + { + throw new HTMLPurifier_Exception( + "Inconsistency in $class: " . HTMLPurifier_VarParser::getTypeName($type) . + " not implemented" + ); } /** * Generic error for if a type didn't work. + * @param mixed $var + * @param int $type */ - protected function errorGeneric($var, $type) { + protected function errorGeneric($var, $type) + { $vtype = gettype($var); - $this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype"); + $this->error("Expected type " . HTMLPurifier_VarParser::getTypeName($type) . ", got $vtype"); } - static public function getTypeName($type) { + /** + * @param int $type + * @return string + */ + public static function getTypeName($type) + { static $lookup; if (!$lookup) { // Lazy load the alternative lookup table $lookup = array_flip(HTMLPurifier_VarParser::$types); } - if (!isset($lookup[$type])) return 'unknown'; + if (!isset($lookup[$type])) { + return 'unknown'; + } return $lookup[$type]; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/VarParser/Flexible.php b/library/HTMLPurifier/VarParser/Flexible.php index c954250e9..b15016c5b 100644 --- a/library/HTMLPurifier/VarParser/Flexible.php +++ b/library/HTMLPurifier/VarParser/Flexible.php @@ -7,28 +7,41 @@ */ class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser { - - protected function parseImplementation($var, $type, $allow_null) { - if ($allow_null && $var === null) return null; + /** + * @param mixed $var + * @param int $type + * @param bool $allow_null + * @return array|bool|float|int|mixed|null|string + * @throws HTMLPurifier_VarParserException + */ + protected function parseImplementation($var, $type, $allow_null) + { + if ($allow_null && $var === null) { + return null; + } switch ($type) { // Note: if code "breaks" from the switch, it triggers a generic // exception to be thrown. Specific errors can be specifically // done here. - case self::MIXED : - case self::ISTRING : - case self::STRING : - case self::TEXT : - case self::ITEXT : + case self::MIXED: + case self::ISTRING: + case self::STRING: + case self::TEXT: + case self::ITEXT: return $var; - case self::INT : - if (is_string($var) && ctype_digit($var)) $var = (int) $var; + case self::INT: + if (is_string($var) && ctype_digit($var)) { + $var = (int)$var; + } return $var; - case self::FLOAT : - if ((is_string($var) && is_numeric($var)) || is_int($var)) $var = (float) $var; + case self::FLOAT: + if ((is_string($var) && is_numeric($var)) || is_int($var)) { + $var = (float)$var; + } return $var; - case self::BOOL : + case self::BOOL: if (is_int($var) && ($var === 0 || $var === 1)) { - $var = (bool) $var; + $var = (bool)$var; } elseif (is_string($var)) { if ($var == 'on' || $var == 'true' || $var == '1') { $var = true; @@ -39,48 +52,70 @@ class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser } } return $var; - case self::ALIST : - case self::HASH : - case self::LOOKUP : + case self::ALIST: + case self::HASH: + case self::LOOKUP: if (is_string($var)) { // special case: technically, this is an array with // a single empty string item, but having an empty // array is more intuitive - if ($var == '') return array(); + if ($var == '') { + return array(); + } if (strpos($var, "\n") === false && strpos($var, "\r") === false) { // simplistic string to array method that only works // for simple lists of tag names or alphanumeric characters - $var = explode(',',$var); + $var = explode(',', $var); } else { $var = preg_split('/(,|[\n\r]+)/', $var); } // remove spaces - foreach ($var as $i => $j) $var[$i] = trim($j); + foreach ($var as $i => $j) { + $var[$i] = trim($j); + } if ($type === self::HASH) { // key:value,key2:value2 $nvar = array(); foreach ($var as $keypair) { $c = explode(':', $keypair, 2); - if (!isset($c[1])) continue; - $nvar[$c[0]] = $c[1]; + if (!isset($c[1])) { + continue; + } + $nvar[trim($c[0])] = trim($c[1]); } $var = $nvar; } } - if (!is_array($var)) break; + if (!is_array($var)) { + break; + } $keys = array_keys($var); if ($keys === array_keys($keys)) { - if ($type == self::ALIST) return $var; - elseif ($type == self::LOOKUP) { + if ($type == self::ALIST) { + return $var; + } elseif ($type == self::LOOKUP) { $new = array(); foreach ($var as $key) { $new[$key] = true; } return $new; - } else break; + } else { + break; + } + } + if ($type === self::ALIST) { + trigger_error("Array list did not have consecutive integer indexes", E_USER_WARNING); + return array_values($var); } if ($type === self::LOOKUP) { foreach ($var as $key => $value) { + if ($value !== true) { + trigger_error( + "Lookup array has non-true value at key '$key'; " . + "maybe your input array was not indexed numerically", + E_USER_WARNING + ); + } $var[$key] = true; } } @@ -90,7 +125,6 @@ class HTMLPurifier_VarParser_Flexible extends HTMLPurifier_VarParser } $this->errorGeneric($var, $type); } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/VarParser/Native.php b/library/HTMLPurifier/VarParser/Native.php index b02a6de54..f11c318ef 100644 --- a/library/HTMLPurifier/VarParser/Native.php +++ b/library/HTMLPurifier/VarParser/Native.php @@ -8,11 +8,24 @@ class HTMLPurifier_VarParser_Native extends HTMLPurifier_VarParser { - protected function parseImplementation($var, $type, $allow_null) { + /** + * @param mixed $var + * @param int $type + * @param bool $allow_null + * @return null|string + */ + protected function parseImplementation($var, $type, $allow_null) + { return $this->evalExpression($var); } - protected function evalExpression($expr) { + /** + * @param string $expr + * @return mixed + * @throws HTMLPurifier_VarParserException + */ + protected function evalExpression($expr) + { $var = null; $result = eval("\$var = $expr;"); if ($result === false) { @@ -20,7 +33,6 @@ class HTMLPurifier_VarParser_Native extends HTMLPurifier_VarParser } return $var; } - } // vim: et sw=4 sts=4 diff --git a/library/HTMLPurifier/Zipper.php b/library/HTMLPurifier/Zipper.php new file mode 100644 index 000000000..6e21ea070 --- /dev/null +++ b/library/HTMLPurifier/Zipper.php @@ -0,0 +1,157 @@ +<?php + +/** + * A zipper is a purely-functional data structure which contains + * a focus that can be efficiently manipulated. It is known as + * a "one-hole context". This mutable variant implements a zipper + * for a list as a pair of two arrays, laid out as follows: + * + * Base list: 1 2 3 4 [ ] 6 7 8 9 + * Front list: 1 2 3 4 + * Back list: 9 8 7 6 + * + * User is expected to keep track of the "current element" and properly + * fill it back in as necessary. (ToDo: Maybe it's more user friendly + * to implicitly track the current element?) + * + * Nota bene: the current class gets confused if you try to store NULLs + * in the list. + */ + +class HTMLPurifier_Zipper +{ + public $front, $back; + + public function __construct($front, $back) { + $this->front = $front; + $this->back = $back; + } + + /** + * Creates a zipper from an array, with a hole in the + * 0-index position. + * @param Array to zipper-ify. + * @return Tuple of zipper and element of first position. + */ + static public function fromArray($array) { + $z = new self(array(), array_reverse($array)); + $t = $z->delete(); // delete the "dummy hole" + return array($z, $t); + } + + /** + * Convert zipper back into a normal array, optionally filling in + * the hole with a value. (Usually you should supply a $t, unless you + * are at the end of the array.) + */ + public function toArray($t = NULL) { + $a = $this->front; + if ($t !== NULL) $a[] = $t; + for ($i = count($this->back)-1; $i >= 0; $i--) { + $a[] = $this->back[$i]; + } + return $a; + } + + /** + * Move hole to the next element. + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function next($t) { + if ($t !== NULL) array_push($this->front, $t); + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Iterated hole advancement. + * @param $t Element to fill hole with + * @param $i How many forward to advance hole + * @return Original contents of new hole, i away + */ + public function advance($t, $n) { + for ($i = 0; $i < $n; $i++) { + $t = $this->next($t); + } + return $t; + } + + /** + * Move hole to the previous element + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function prev($t) { + if ($t !== NULL) array_push($this->back, $t); + return empty($this->front) ? NULL : array_pop($this->front); + } + + /** + * Delete contents of current hole, shifting hole to + * next element. + * @return Original contents of new hole. + */ + public function delete() { + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Returns true if we are at the end of the list. + * @return bool + */ + public function done() { + return empty($this->back); + } + + /** + * Insert element before hole. + * @param Element to insert + */ + public function insertBefore($t) { + if ($t !== NULL) array_push($this->front, $t); + } + + /** + * Insert element after hole. + * @param Element to insert + */ + public function insertAfter($t) { + if ($t !== NULL) array_push($this->back, $t); + } + + /** + * Splice in multiple elements at hole. Functional specification + * in terms of array_splice: + * + * $arr1 = $arr; + * $old1 = array_splice($arr1, $i, $delete, $replacement); + * + * list($z, $t) = HTMLPurifier_Zipper::fromArray($arr); + * $t = $z->advance($t, $i); + * list($old2, $t) = $z->splice($t, $delete, $replacement); + * $arr2 = $z->toArray($t); + * + * assert($old1 === $old2); + * assert($arr1 === $arr2); + * + * NB: the absolute index location after this operation is + * *unchanged!* + * + * @param Current contents of hole. + */ + public function splice($t, $delete, $replacement) { + // delete + $old = array(); + $r = $t; + for ($i = $delete; $i > 0; $i--) { + $old[] = $r; + $r = $this->delete(); + } + // insert + for ($i = count($replacement)-1; $i >= 0; $i--) { + $this->insertAfter($r); + $r = $replacement[$i]; + } + return array($old, $r); + } +} |